OpenAI + LLM Security + Web Labs Study Plan

gitgud.blog

OpenAI Cookbook + LLM Security + Web Labs Study Plan

523 resources ranked from foundational to hard, scheduled from 2026-05-09 through 2026-08-31. Each day starts with an Embrace The Red reading before the OpenAI Cookbook work, then ends with a PortSwigger Web Security Academy lab. Use the checklist to track what you have studied; go deep only when a resource earns it.

523 resources
115 study days
4-5 per day
0 studied
523 of 523 Progress is private to this browser.
Done Rank Resource Plan Level Product Tags Source
2026-05-09 0 of 5 studied
#1
Getting the hang of machine learning Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-09
1 of 5 		Foundation LLM Security embrace-the-red, llm-security, ai-security Open
#2
How to count tokens with Tiktoken
2026-05-09
2 of 5 		Foundation OpenAI API tiktoken, completions Open
#3
How to format inputs to ChatGPT models
2026-05-09
3 of 5 		Foundation OpenAI API completions, tiktoken Open
#4
GPT-5 Troubleshooting Guide
2026-05-09
4 of 5 		Foundation Prompting gpt-5, prompt-optimization Open
#5
Manipulating WebSocket messages to exploit vulnerabilities WebSockets lab (apprentice).
2026-05-09
5 of 5 		Easy PortSwigger Labs portswigger, web-security, websockets, apprentice Open
2026-05-10 0 of 5 studied
#6
The machine learning pipeline and attacks Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-10
1 of 5 		Foundation LLM Security embrace-the-red, llm-security, ai-security Open
#7
GPT-4.1 Prompting Guide
2026-05-10
2 of 5 		Foundation Responses API responses, api Open
#8
How to stream completions
2026-05-10
3 of 5 		Foundation OpenAI API completions Open
#9
How to work with large language models
2026-05-10
4 of 5 		Foundation OpenAI API completions Open
#10
Cross-site WebSocket hijacking WebSockets lab (practitioner).
2026-05-10
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, websockets, practitioner Open
2026-05-11 0 of 5 studied
#11
Husky AI: Building a machine learning system Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-11
1 of 5 		Foundation LLM Security embrace-the-red, llm-security, ai-security Open
#12
How to make your completions outputs consistent with the new seed parameter
2026-05-11
2 of 5 		Foundation OpenAI API completions Open
#13
GPT-5.1 Prompting Guide
2026-05-11
3 of 5 		Foundation OpenAI API gpt-5.1 Open
#14
GPT-5.2 Prompting Guide Cookbook to prompt GPT-5.2 for accurate, concise enterprise workflows.
2026-05-11
4 of 5 		Foundation OpenAI API gpt-5.2 Open
#15
Manipulating the WebSocket handshake to exploit vulnerabilities WebSockets lab (practitioner).
2026-05-11
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, websockets, practitioner Open
2026-05-12 0 of 5 studied
#16
Threat modeling a machine learning system Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-12
1 of 5 		Foundation LLM Security embrace-the-red, llm-security, ai-security Open
#17
Question answering using embeddings-based search
2026-05-12
2 of 5 		Foundation Embeddings and Retrieval embeddings, completions Open
#18
Question answering using a search API and re-ranking
2026-05-12
3 of 5 		Foundation Embeddings and Retrieval embeddings, completions Open
#19
Translate a book writen in LaTeX from Slovenian into English
2026-05-12
4 of 5 		Foundation OpenAI API completions, tiktoken Open
#20
Authentication bypass via OAuth implicit flow OAuth authentication lab (apprentice).
2026-05-12
5 of 5 		Easy PortSwigger Labs portswigger, web-security, oauth-authentication, apprentice Open
2026-05-13 0 of 5 studied
#21
Machine Learning Attack Series: Overview Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-13
1 of 5 		Foundation LLM Security embrace-the-red, llm-security, ai-security Open
#22
Techniques to improve reliability
2026-05-13
2 of 5 		Foundation OpenAI API completions Open
#23
Unit test writing using a multi-step prompt
2026-05-13
3 of 5 		Foundation OpenAI API completions Open
#24
Long document content extraction
2026-05-13
4 of 5 		Foundation OpenAI API completions Open
#25
SSRF via OpenID dynamic client registration OAuth authentication lab (practitioner).
2026-05-13
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, oauth-authentication, practitioner Open
2026-05-14 0 of 5 studied
#26
Video: Prompt Injections - An Introduction Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-14
1 of 5 		Foundation LLM Security embrace-the-red, llm-security, prompt-injection Open
#27
Unit test writing using a multi-step prompt with legacy Completions
2026-05-14
2 of 5 		Foundation OpenAI API completions Open
#28
OpenAI API Monitoring with Weights & Biases Weave
2026-05-14
3 of 5 		Foundation OpenAI API tiktoken, completions Open
#29
Using logprobs
2026-05-14
4 of 5 		Foundation OpenAI API completions Open
#30
Forced OAuth profile linking OAuth authentication lab (practitioner).
2026-05-14
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, oauth-authentication, practitioner Open
2026-05-15 0 of 5 studied
#31
Adversarial Prompting: Tutorial and Lab Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-15
1 of 5 		Foundation LLM Security embrace-the-red, llm-security, prompt-injection, ai-security Open
#32
Synthetic data generation (Part 1)
2026-05-15
2 of 5 		Foundation OpenAI API completions Open
#33
Summarizing Long Documents
2026-05-15
3 of 5 		Foundation OpenAI API chat Open
#34
Using reasoning for data validation
2026-05-15
4 of 5 		Foundation OpenAI API completions, reasoning Open
#35
OAuth account hijacking via redirect_uri OAuth authentication lab (practitioner).
2026-05-15
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, oauth-authentication, practitioner Open
2026-05-16 0 of 5 studied
#36
AI Injections: Direct and Indirect Prompt Injections and Their Implications Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-16
1 of 5 		Foundation LLM Security embrace-the-red, llm-security, prompt-injection Open
#37
Using reasoning for routine generation
2026-05-16
2 of 5 		Foundation OpenAI API completions, reasoning Open
#38
Prompt Caching 101 Cookbook to reduce latency and cost using OpenAI prompt caching.
2026-05-16
3 of 5 		Foundation OpenAI API latency, cost, prompt caching, completions Open
#39
Enhance your prompts with meta prompting
2026-05-16
4 of 5 		Foundation OpenAI API completions, reasoning Open
#40
Stealing OAuth access tokens via an open redirect OAuth authentication lab (practitioner).
2026-05-16
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, oauth-authentication, practitioner Open
2026-05-17 0 of 5 studied
#41
Don't blindly trust LLM responses. Threats to chatbots. Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-17
1 of 5 		Foundation LLM Security embrace-the-red, llm-security Open
#42
Reasoning over Code Quality and Security in GitHub Pull Requests
2026-05-17
2 of 5 		Foundation OpenAI API SDLC, reasoning, completions Open
#43
GPT-5 prompting guide
2026-05-17
3 of 5 		Foundation Responses API gpt-5, responses, reasoning Open
#44
Clustering for transaction classification
2026-05-17
4 of 5 		Foundation Embeddings and Retrieval embeddings, completions Open
#45
Stealing OAuth access tokens via a proxy page OAuth authentication lab (expert).
2026-05-17
5 of 5 		Hard PortSwigger Labs portswigger, web-security, oauth-authentication, expert Open
2026-05-18 0 of 5 studied
#46
MLSecOps Podcast: AI Red Teaming and Threat Modeling Machine Learning Systems Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-18
1 of 5 		Foundation LLM Security embrace-the-red, llm-security, ai-security Open
#47
Multiclass Classification for Transactions
2026-05-18
2 of 5 		Foundation Embeddings and Retrieval embeddings, completions Open
#48
Robust question answering with Chroma and OpenAI
2026-05-18
3 of 5 		Foundation Embeddings and Retrieval embeddings, completions Open
#49
Getting Started with OpenAI Evals
2026-05-18
4 of 5 		Foundation OpenAI API completions Open
#50
Exploiting LLM APIs with excessive agency Web LLM attacks lab (apprentice).
2026-05-18
5 of 5 		Easy PortSwigger Labs portswigger, web-security, web-llm-attacks, apprentice Open
2026-05-19 0 of 5 studied
#51
Video: Data Exfiltration Vulnerabilities in LLM apps (Bing Chat, ChatGPT, Claude) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-19
1 of 5 		Foundation LLM Security embrace-the-red, llm-security, data-exfiltration Open
#52
Using chained calls for o1 structured outputs
2026-05-19
2 of 5 		Foundation OpenAI API completions, reasoning Open
#53
How to handle rate limits
2026-05-19
3 of 5 		Foundation Embeddings and Retrieval completions, embeddings Open
#54
Prompt Migration Guide
2026-05-19
4 of 5 		Foundation Responses API prompt, completions, responses Open
#55
Exploiting vulnerabilities in LLM APIs Web LLM attacks lab (practitioner).
2026-05-19
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, web-llm-attacks, practitioner Open
2026-05-20 0 of 5 studied
#56
HITCON CMT 2023 - LLM Security Presentation and Trip Report Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-20
1 of 5 		Foundation LLM Security embrace-the-red, llm-security Open
#57
Search reranking with cross-encoders
2026-05-20
2 of 5 		Foundation Embeddings and Retrieval embeddings, completions Open
#58
Embedding Wikipedia articles for search
2026-05-20
3 of 5 		Foundation Embeddings and Retrieval embeddings, completions Open
#59
Embedding texts that are longer than the model's maximum context length
2026-05-20
4 of 5 		Foundation Embeddings and Retrieval embeddings, tiktoken Open
#60
Indirect prompt injection Web LLM attacks lab (practitioner).
2026-05-20
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, web-llm-attacks, practitioner Open
2026-05-21 0 of 5 studied
#61
Machine Learning Attack Series: Adversarial Robustness Toolbox Basics Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-21
1 of 5 		Easy LLM Security embrace-the-red, llm-security, ai-security Open
#62
Question answering with Langchain, Tair and OpenAI
2026-05-21
2 of 5 		Foundation Embeddings and Retrieval embeddings, tiktoken, completions Open
#63
Handling Function Calls with Reasoning Models
2026-05-21
3 of 5 		Foundation Responses API reasoning, functions, responses, api Open
#64
o3/o4-mini Function Calling Guide Cookbook to improve o3/o4-mini function calling with prompt best practices.
2026-05-21
4 of 5 		Foundation Responses API functions, responses, reasoning Open
#65
Exploiting insecure output handling in LLMs Web LLM attacks lab (expert).
2026-05-21
5 of 5 		Hard PortSwigger Labs portswigger, web-security, web-llm-attacks, expert Open
2026-05-22 0 of 5 studied
#66
GPT-3 and Phishing Attacks Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-22
1 of 5 		Easy LLM Security embrace-the-red, llm-security Open
#67
Related resources from around the web
2026-05-22
2 of 5 		Foundation Embeddings and Retrieval completions, embeddings Open
#68
RAG with a Graph database
2026-05-22
3 of 5 		Foundation Embeddings and Retrieval embeddings, completions Open
#69
What makes documentation good
2026-05-22
4 of 5 		Foundation OpenAI API Open
#70
Exploiting AI agents to perform destructive actions Web LLM attacks lab (apprentice).
2026-05-22
5 of 5 		Easy PortSwigger Labs portswigger, web-security, web-llm-attacks, apprentice Open
2026-05-23 0 of 5 studied
#71
Machine Learning Attack Series: Backdooring Pickle Files Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-23
1 of 5 		Easy LLM Security embrace-the-red, llm-security, ai-security Open
#72
Prompt Personalities Cookbook to shape agent personality via instruction prompts for tone and style.
2026-05-23
2 of 5 		Foundation OpenAI API gpt-5, prompt-personalities Open
#73
How to evaluate a summarization task
2026-05-23
3 of 5 		Foundation Embeddings and Retrieval embeddings, completions Open
#74
How to automate AWS tasks with function calling
2026-05-23
4 of 5 		Foundation Embeddings and Retrieval completions, embeddings, functions Open
#75
Exploiting AI agents to exfiltrate sensitive information Web LLM attacks lab (apprentice).
2026-05-23
5 of 5 		Easy PortSwigger Labs portswigger, web-security, web-llm-attacks, apprentice Open
2026-05-24 0 of 5 studied
#76
ChatGPT: Imagine you are a database server Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-24
1 of 5 		Easy LLM Security embrace-the-red, llm-security Open
#77
Clustering
2026-05-24
2 of 5 		Foundation Embeddings and Retrieval embeddings Open
#78
Zero-shot classification with embeddings
2026-05-24
3 of 5 		Foundation Embeddings and Retrieval embeddings Open
#79
Classification using embeddings
2026-05-24
4 of 5 		Foundation Embeddings and Retrieval embeddings Open
#80
Exploiting AI agents to trigger secondary vulnerabilities Web LLM attacks lab (practitioner).
2026-05-24
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, web-llm-attacks, practitioner Open
2026-05-25 0 of 5 studied
#81
Yolo: Natural Language to Shell Commands with ChatGPT API Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-25
1 of 5 		Easy LLM Security embrace-the-red, llm-security Open
#82
Frontend coding with GPT-5
2026-05-25
2 of 5 		Foundation Responses API gpt-5, responses, reasoning Open
#83
Skills in OpenAI API Cookbook for building skills with the OpenAI API.
2026-05-25
3 of 5 		Foundation Responses API responses Open
#84
Introduction to Structured Outputs
2026-05-25
4 of 5 		Foundation Tool Calling completions, functions Open
#85
Bypassing AI scanner defenses to exfiltrate sensitive information Web LLM attacks lab (practitioner).
2026-05-25
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, web-llm-attacks, practitioner Open
2026-05-26 0 of 5 studied
#86
Machine Learning Attack Series: Backdooring Keras Models and How to Detect It Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-26
1 of 5 		Easy LLM Security embrace-the-red, llm-security, ai-security Open
#87
Azure Chat Completions example (preview)
2026-05-26
2 of 5 		Foundation OpenAI API completions Open
#88
Azure Chat Completion models with your own data (preview)
2026-05-26
3 of 5 		Foundation OpenAI API completions Open
#89
Build Your Own Code Interpreter - Dynamic Tool Generation and Execution With o3-mini
2026-05-26
4 of 5 		Foundation OpenAI API completions Open
#90
Exploiting an API endpoint using documentation API testing lab (apprentice).
2026-05-26
5 of 5 		Easy PortSwigger Labs portswigger, web-security, api-testing, apprentice Open
2026-05-27 0 of 5 studied
#91
ASCII Smuggler Tool: Crafting Invisible Text and Decoding Hidden Codes Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-27
1 of 5 		Easy LLM Security embrace-the-red, llm-security Open
#92
Code search using embeddings
2026-05-27
2 of 5 		Foundation Embeddings and Retrieval embeddings Open
#93
Recommendation using embeddings and nearest neighbor search
2026-05-27
3 of 5 		Foundation Embeddings and Retrieval embeddings Open
#94
Semantic text search using embeddings
2026-05-27
4 of 5 		Foundation Embeddings and Retrieval embeddings Open
#95
Exploiting server-side parameter pollution in a query string API testing lab (practitioner).
2026-05-27
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, api-testing, practitioner Open
2026-05-28 0 of 5 studied
#96
Hidden Prompt Injections with Anthropic Claude Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-28
1 of 5 		Easy LLM Security embrace-the-red, llm-security, prompt-injection Open
#97
Question Answering in Weaviate with OpenAI Q&A module
2026-05-28
2 of 5 		Foundation Embeddings and Retrieval embeddings, completions Open
#98
Using Chroma for embeddings search
2026-05-28
3 of 5 		Foundation Embeddings and Retrieval embeddings Open
#99
Using Typesense for embeddings search
2026-05-28
4 of 5 		Foundation Embeddings and Retrieval embeddings Open
#100
Finding and exploiting an unused API endpoint API testing lab (practitioner).
2026-05-28
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, api-testing, practitioner Open
2026-05-29 0 of 5 studied
#101
Video: ASCII Smuggling and Hidden Prompt Instructions Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-29
1 of 5 		Easy LLM Security embrace-the-red, llm-security, prompt-injection Open
#102
Semantic search using Supabase Vector
2026-05-29
2 of 5 		Foundation Embeddings and Retrieval embeddings Open
#103
Doing RAG on PDFs using File Search in the Responses API Cookbook to search PDFs with the Responses API file search tool.
2026-05-29
3 of 5 		Foundation Responses API responses, functions Open
#104
Web Search and States with Responses API
2026-05-29
4 of 5 		Foundation Responses API responses, web-search, functions Open
#105
Exploiting a mass assignment vulnerability API testing lab (practitioner).
2026-05-29
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, api-testing, practitioner Open
2026-05-30 0 of 5 studied
#106
Google Gemini: Planting Instructions For Delayed Automatic Tool Invocation Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-30
1 of 5 		Easy LLM Security embrace-the-red, llm-security Open
#107
Question answering with Langchain, AnalyticDB and OpenAI
2026-05-30
2 of 5 		Foundation Embeddings and Retrieval embeddings, tiktoken Open
#108
Customizing embeddings
2026-05-30
3 of 5 		Foundation Embeddings and Retrieval embeddings Open
#109
Get embeddings from dataset
2026-05-30
4 of 5 		Foundation Embeddings and Retrieval embeddings Open
#110
Exploiting server-side parameter pollution in a REST URL API testing lab (expert).
2026-05-30
5 of 5 		Hard PortSwigger Labs portswigger, web-security, api-testing, expert Open
2026-05-31 0 of 5 studied
#111
The dangers of AI agents unfurling hyperlinks and what to do about it Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-05-31
1 of 5 		Easy LLM Security embrace-the-red, llm-security, agents Open
#112
Regression using the embeddings
2026-05-31
2 of 5 		Foundation Embeddings and Retrieval embeddings Open
#113
User and product embeddings
2026-05-31
3 of 5 		Foundation Embeddings and Retrieval embeddings Open
#114
Using embeddings
2026-05-31
4 of 5 		Foundation Embeddings and Retrieval embeddings Open
#115
Limit overrun race conditions Race conditions lab (apprentice).
2026-05-31
5 of 5 		Easy PortSwigger Labs portswigger, web-security, race-conditions, apprentice Open
2026-06-01 0 of 5 studied
#116
Automatic Tool Invocation when Browsing with ChatGPT - Threats and Mitigations Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-01
1 of 5 		Easy LLM Security embrace-the-red, llm-security Open
#117
Visualizing embeddings in 3D
2026-06-01
2 of 5 		Foundation Embeddings and Retrieval embeddings Open
#118
Visualizing the embeddings in 2D
2026-06-01
3 of 5 		Foundation Embeddings and Retrieval embeddings Open
#119
Use cases for embeddings
2026-06-01
4 of 5 		Foundation Embeddings and Retrieval embeddings Open
#120
Bypassing rate limits via race conditions Race conditions lab (practitioner).
2026-06-01
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, race-conditions, practitioner Open
2026-06-02 0 of 5 studied
#121
Trust No AI: Prompt Injection Along the CIA Security Triad Paper Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-02
1 of 5 		Easy LLM Security embrace-the-red, llm-security, prompt-injection Open
#122
Visualizing embeddings in Weights and Biases
2026-06-02
2 of 5 		Foundation Embeddings and Retrieval embeddings Open
#123
Visualizing embeddings in Atlas
2026-06-02
3 of 5 		Foundation Embeddings and Retrieval embeddings Open
#124
Using AnalyticDB as a vector database for OpenAI embeddings
2026-06-02
4 of 5 		Foundation Embeddings and Retrieval embeddings Open
#125
Multi-endpoint race conditions Race conditions lab (practitioner).
2026-06-02
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, race-conditions, practitioner Open
2026-06-03 0 of 5 studied
#126
The Normalization of Deviance in AI Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-03
1 of 5 		Easy LLM Security embrace-the-red, llm-security Open
#127
Typesense
2026-06-03
2 of 5 		Foundation Embeddings and Retrieval embeddings Open
#128
Kusto as a vector database
2026-06-03
3 of 5 		Foundation Embeddings and Retrieval embeddings Open
#129
Kusto as a vector database for embeddings
2026-06-03
4 of 5 		Foundation Embeddings and Retrieval embeddings Open
#130
Single-endpoint race conditions Race conditions lab (practitioner).
2026-06-03
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, race-conditions, practitioner Open
2026-06-04 0 of 5 studied
#131
Given Enough Agents, All Bugs Become Shallow Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-04
1 of 5 		Easy LLM Security embrace-the-red, llm-security, agents Open
#132
Using Hologres as a vector database for OpenAI embeddings
2026-06-04
2 of 5 		Foundation Embeddings and Retrieval embeddings Open
#133
Vector databases
2026-06-04
3 of 5 		Foundation Embeddings and Retrieval embeddings Open
#134
Using PolarDB-PG as a vector database for OpenAI embeddings
2026-06-04
4 of 5 		Foundation Embeddings and Retrieval embeddings Open
#135
Exploiting time-sensitive vulnerabilities Race conditions lab (practitioner).
2026-06-04
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, race-conditions, practitioner Open
2026-06-05 0 of 5 studied
#136
Indirect Prompt Injection via YouTube Transcripts Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-05
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection Open
#137
Visualizing the embeddings in Kangas
2026-06-05
2 of 5 		Foundation Embeddings and Retrieval embeddings Open
#138
Using Tair as a vector database for OpenAI embeddings
2026-06-05
3 of 5 		Foundation Embeddings and Retrieval embeddings Open
#139
Neon as a vector database
2026-06-05
4 of 5 		Foundation Embeddings and Retrieval embeddings Open
#140
Partial construction race conditions Race conditions lab (expert).
2026-06-05
5 of 5 		Hard PortSwigger Labs portswigger, web-security, race-conditions, expert Open
2026-06-06 0 of 5 studied
#141
ChatGPT Plugins: Data Exfiltration via Images & Cross Plugin Request Forgery Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-06
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#142
Supabase Vector Database
2026-06-06
2 of 5 		Foundation Embeddings and Retrieval embeddings Open
#143
Better performance from reasoning models using the Responses API
2026-06-06
3 of 5 		Easy Responses API responses, functions Open
#144
Semantic search with SingleStoreDB
2026-06-06
4 of 5 		Easy Embeddings and Retrieval completions, embeddings Open
#145
Exploiting XXE using external entities to retrieve files XML external entity (XXE) injection lab (apprentice).
2026-06-06
5 of 5 		Easy PortSwigger Labs portswigger, web-security, xml-external-entity-xxe-injection, apprentice Open
2026-06-07 0 of 5 studied
#146
ChatGPT Plugin Exploit Explained: From Prompt Injection to Accessing Private Data Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-07
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection Open
#147
Using Weaviate with generative OpenAI module for generative search
2026-06-07
2 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#148
Elasticsearch
2026-06-07
3 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#149
Getting Started with Zilliz and OpenAI
2026-06-07
4 of 5 		Easy Embeddings and Retrieval embeddings Open
#150
Exploiting XXE to perform SSRF attacks XML external entity (XXE) injection lab (apprentice).
2026-06-07
5 of 5 		Easy PortSwigger Labs portswigger, web-security, xml-external-entity-xxe-injection, apprentice Open
2026-06-08 0 of 5 studied
#151
Bing Chat: Data Exfiltration Exploit Explained Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-08
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#152
Getting started with Milvus and OpenAI
2026-06-08
2 of 5 		Easy Embeddings and Retrieval embeddings Open
#153
Function calling for nearby places: Leveraging the Google Places API and customer profiles
2026-06-08
3 of 5 		Easy Tool Calling completions, functions Open
#154
Function calling with an OpenAPI specification
2026-06-08
4 of 5 		Easy Tool Calling completions, functions Open
#155
Blind XXE with out-of-band interaction XML external entity (XXE) injection lab (practitioner).
2026-06-08
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, xml-external-entity-xxe-injection, practitioner Open
2026-06-09 0 of 5 studied
#156
ChatGPT Custom Instructions: Persistent Data Exfiltration Demo Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-09
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration, persistence Open
#157
Named Entity Recognition to Enrich Text
2026-06-09
2 of 5 		Easy Tool Calling completions, functions Open
#158
Batch processing with the Batch API
2026-06-09
3 of 5 		Easy Batch API batch, completions Open
#159
How to use the Usage API and Cost API to monitor your OpenAI usage Cookbook to fetch and visualize Completions Usage and cost data via API.
2026-06-09
4 of 5 		Easy Usage API usage-api, cost-api Open
#160
Blind XXE with out-of-band interaction via XML parameter entities XML external entity (XXE) injection lab (practitioner).
2026-06-09
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, xml-external-entity-xxe-injection, practitioner Open
2026-06-10 0 of 5 studied
#161
Malicious ChatGPT Agents: How GPTs Can Quietly Grab Your Data (Demo) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-10
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, agents Open
#162
Redis
2026-06-10
2 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#163
Pinecone vector database
2026-06-10
3 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#164
Retrieval augmentation for GPT-4 using Pinecone
2026-06-10
4 of 5 		Easy Embeddings and Retrieval embeddings, completions, tiktoken Open
#165
Exploiting blind XXE to exfiltrate data using a malicious external DTD XML external entity (XXE) injection lab (practitioner).
2026-06-10
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, xml-external-entity-xxe-injection, practitioner Open
2026-06-11 0 of 5 studied
#166
Exploring Google Bard's Data Visualization Feature (Code Interpreter) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-11
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security Open
#167
Redis as a context store with Chat Completions
2026-06-11
2 of 5 		Easy Embeddings and Retrieval completions, embeddings Open
#168
SingleStoreDB
2026-06-11
3 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#169
Philosophy with vector embeddings, OpenAI and Cassandra / Astra DB
2026-06-11
4 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#170
Exploiting blind XXE to retrieve data via error messages XML external entity (XXE) injection lab (practitioner).
2026-06-11
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, xml-external-entity-xxe-injection, practitioner Open
2026-06-12 0 of 5 studied
#171
ChatGPT: Lack of Isolation between Code Interpreter sessions of GPTs Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-12
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security Open
#172
Philosophy with vector embeddings, OpenAI and Cassandra / Astra DB
2026-06-12
2 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#173
MongoDB Atlas Vector Search
2026-06-12
3 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#174
Semantic search using MongoDB Atlas Vector Search and OpenAI
2026-06-12
4 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#175
Exploiting XInclude to retrieve files XML external entity (XXE) injection lab (practitioner).
2026-06-12
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, xml-external-entity-xxe-injection, practitioner Open
2026-06-13 0 of 5 studied
#176
Breaking Instruction Hierarchy in OpenAI's gpt-4o-mini Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-13
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security Open
#177
Building a Bring Your Own Browser (BYOB) Tool for Web Browsing and Summarization
2026-06-13
2 of 5 		Easy OpenAI API completions Open
#178
Financial document analysis with LlamaIndex
2026-06-13
3 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#179
Whisper prompting guide
2026-06-13
4 of 5 		Easy Audio whisper, completions Open
#180
Exploiting XXE via image file upload XML external entity (XXE) injection lab (practitioner).
2026-06-13
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, xml-external-entity-xxe-injection, practitioner Open
2026-06-14 0 of 5 studied
#181
ChatGPT Operator: Prompt Injection Exploits & Defenses Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-14
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection, agents Open
#182
Retrieval augmented generative question answering with Pinecone
2026-06-14
2 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#183
Question answering with LangChain, Deep Lake, & OpenAI
2026-06-14
3 of 5 		Easy Embeddings and Retrieval embeddings Open
#184
Using Weaviate with OpenAI vectorize module for embeddings search
2026-06-14
4 of 5 		Easy Embeddings and Retrieval embeddings Open
#185
Exploiting XXE to retrieve data by repurposing a local DTD XML external entity (XXE) injection lab (expert).
2026-06-14
5 of 5 		Hard PortSwigger Labs portswigger, web-security, xml-external-entity-xxe-injection, expert Open
2026-06-15 0 of 5 studied
#186
GitHub Copilot Custom Instructions and Risks Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-15
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security Open
#187
Using Weaviate with OpenAI vectorize module for hybrid search
2026-06-15
2 of 5 		Easy Embeddings and Retrieval embeddings Open
#188
Semantic search with Pinecone and OpenAI
2026-06-15
3 of 5 		Easy Embeddings and Retrieval embeddings Open
#189
Filtered Search with Zilliz and OpenAI
2026-06-15
4 of 5 		Easy Embeddings and Retrieval embeddings Open
#190
Basic SSRF against the local server Server-side request forgery (SSRF) lab (apprentice).
2026-06-15
5 of 5 		Easy PortSwigger Labs portswigger, web-security, server-side-request-forgery-ssrf, apprentice Open
2026-06-16 0 of 5 studied
#191
Anthropic Claude Data Exfiltration Vulnerability Fixed Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-16
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#192
Filtered search with Milvus and OpenAI
2026-06-16
2 of 5 		Easy Embeddings and Retrieval embeddings Open
#193
Using Pinecone for embeddings search
2026-06-16
3 of 5 		Easy Embeddings and Retrieval embeddings Open
#194
Using Qdrant for embeddings search
2026-06-16
4 of 5 		Easy Embeddings and Retrieval embeddings Open
#195
Basic SSRF against another back-end system Server-side request forgery (SSRF) lab (apprentice).
2026-06-16
5 of 5 		Easy PortSwigger Labs portswigger, web-security, server-side-request-forgery-ssrf, apprentice Open
2026-06-17 0 of 5 studied
#196
Microsoft Fixes Data Exfiltration Vulnerability in Azure AI Playground Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-17
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#197
Using Redis for embeddings search
2026-06-17
2 of 5 		Easy Embeddings and Retrieval embeddings Open
#198
Using Weaviate for embeddings search
2026-06-17
3 of 5 		Easy Embeddings and Retrieval embeddings Open
#199
Semantic search using Elasticsearch and OpenAI
2026-06-17
4 of 5 		Easy Embeddings and Retrieval embeddings Open
#200
Blind SSRF with out-of-band detection Server-side request forgery (SSRF) lab (practitioner).
2026-06-17
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, server-side-request-forgery-ssrf, practitioner Open
2026-06-18 0 of 5 studied
#201
Google Cloud Vertex AI - Data Exfiltration Vulnerability Fixed in Generative AI Studio Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-18
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#202
Azure AI Search as a vector database for OpenAI embeddings
2026-06-18
2 of 5 		Easy Embeddings and Retrieval embeddings Open
#203
Vector similarity search using Neon Postgres
2026-06-18
3 of 5 		Easy Embeddings and Retrieval embeddings Open
#204
How to call functions with chat models
2026-06-18
4 of 5 		Easy Tool Calling completions, functions Open
#205
SSRF with blacklist-based input filter Server-side request forgery (SSRF) lab (practitioner).
2026-06-18
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, server-side-request-forgery-ssrf, practitioner Open
2026-06-19 0 of 5 studied
#206
Hacking Google Bard - From Prompt Injection to Data Exfiltration Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-19
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection, data-exfiltration Open
#207
How to use functions with a knowledge base
2026-06-19
2 of 5 		Easy Tool Calling completions, functions Open
#208
Assistants API Overview (Python SDK)
2026-06-19
3 of 5 		Easy Tool Calling assistants, functions Open
#209
Image Understanding with RAG
2026-06-19
4 of 5 		Easy Responses API responses, images, RAG, vision Open
#210
SSRF with filter bypass via open redirection vulnerability Server-side request forgery (SSRF) lab (practitioner).
2026-06-19
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, server-side-request-forgery-ssrf, practitioner Open
2026-06-20 0 of 5 studied
#211
OpenAI Begins Tackling ChatGPT Data Leak Vulnerability Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-20
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#212
Azure embeddings example
2026-06-20
2 of 5 		Easy Embeddings and Retrieval embeddings Open
#213
Using Redis as a vector database with OpenAI
2026-06-20
3 of 5 		Easy Embeddings and Retrieval embeddings Open
#214
Weaviate <> OpenAI
2026-06-20
4 of 5 		Easy Embeddings and Retrieval embeddings Open
#215
Blind SSRF with Shellshock exploitation Server-side request forgery (SSRF) lab (expert).
2026-06-20
5 of 5 		Hard PortSwigger Labs portswigger, web-security, server-side-request-forgery-ssrf, expert Open
2026-06-21 0 of 5 studied
#216
AWS Fixes Data Exfiltration Attack Angle in Amazon Q for Business Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-21
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#217
Using Qdrant as a vector database for OpenAI embeddings
2026-06-21
2 of 5 		Easy Embeddings and Retrieval embeddings Open
#218
Running hybrid VSS queries with Redis and OpenAI
2026-06-21
3 of 5 		Easy Embeddings and Retrieval embeddings Open
#219
Using MyScale for embeddings search
2026-06-21
4 of 5 		Easy Embeddings and Retrieval embeddings Open
#220
SSRF with whitelist-based input filter Server-side request forgery (SSRF) lab (expert).
2026-06-21
5 of 5 		Hard PortSwigger Labs portswigger, web-security, server-side-request-forgery-ssrf, expert Open
2026-06-22 0 of 5 studied
#221
Google AI Studio Data Exfiltration via Prompt Injection - Possible Regression and Fix Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-22
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection, data-exfiltration Open
#222
Cassandra / Astra DB
2026-06-22
2 of 5 		Easy Embeddings and Retrieval embeddings Open
#223
Retrieval augmented generation using Elasticsearch and OpenAI
2026-06-22
3 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#224
How to use the moderation API
2026-06-22
4 of 5 		Easy Safety moderation Open
#225
Accessing private GraphQL posts GraphQL API vulnerabilities lab (apprentice).
2026-06-22
5 of 5 		Easy PortSwigger Labs portswigger, web-security, graphql-api-vulnerabilities, apprentice Open
2026-06-23 0 of 5 studied
#226
Bobby Tables but with LLM Apps - Google NotebookLM Data Exfiltration Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-23
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#227
Introduction to GPT-4o and GPT-4o mini
2026-06-23
2 of 5 		Easy Audio completions, vision, whisper Open
#228
Using MyScale as a vector database for OpenAI embeddings
2026-06-23
3 of 5 		Easy Embeddings and Retrieval embeddings Open
#229
Redis vectors as JSON with OpenAI
2026-06-23
4 of 5 		Easy Embeddings and Retrieval embeddings Open
#230
Accidental exposure of private GraphQL fields GraphQL API vulnerabilities lab (practitioner).
2026-06-23
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, graphql-api-vulnerabilities, practitioner Open
2026-06-24 0 of 5 studied
#231
ChatGPT: Hacking Memories with Prompt Injection Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-24
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection Open
#232
Using tool required for customer service
2026-06-24
2 of 5 		Easy Tool Calling completions, functions Open
#233
GPT Actions library - getting started
2026-06-24
3 of 5 		Easy ChatGPT gpt-actions-library, chatgpt Open
#234
Using GPT4 Vision with Function Calling
2026-06-24
4 of 5 		Easy Images and Vision chat, vision Open
#235
Finding a hidden GraphQL endpoint GraphQL API vulnerabilities lab (practitioner).
2026-06-24
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, graphql-api-vulnerabilities, practitioner Open
2026-06-25 0 of 5 studied
#236
GitHub Copilot Chat: From Prompt Injection to Data Exfiltration Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-25
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection, data-exfiltration Open
#237
Addressing transcription misspellings: prompt vs post-processing
2026-06-25
2 of 5 		Easy Audio whisper, completions Open
#238
ChatGPT Enterprise Prompting Guide Cookbook for writing better prompts for everyday work in ChatGPT Enterprise.
2026-06-25
3 of 5 		Easy ChatGPT chatgpt Open
#239
How to combine GPT4o mini with RAG to create a clothing matchmaker app
2026-06-25
4 of 5 		Easy Images and Vision vision, embeddings Open
#240
Bypassing GraphQL brute force protections GraphQL API vulnerabilities lab (practitioner).
2026-06-25
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, graphql-api-vulnerabilities, practitioner Open
2026-06-26 0 of 5 studied
#241
Sorry, ChatGPT Is Under Maintenance: Persistent Denial of Service through Prompt Injection and Memory Attacks Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-26
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection, persistence Open
#242
How to parse PDF docs for RAG
2026-06-26
2 of 5 		Easy Images and Vision vision, embeddings Open
#243
How to use the DALLE API
2026-06-26
3 of 5 		Easy Image Generation dall-e Open
#244
How to create dynamic masks with DALLE and Segment Anything
2026-06-26
4 of 5 		Easy Image Generation dall-e Open
#245
Performing CSRF exploits over GraphQL GraphQL API vulnerabilities lab (practitioner).
2026-06-26
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, graphql-api-vulnerabilities, practitioner Open
2026-06-27 0 of 5 studied
#246
Google Colab AI: Data Leakage Through Image Rendering Fixed. Some Risks Remain. Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-27
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#247
Temporal Agents with Knowledge Graphs
2026-06-27
2 of 5 		Easy Responses API knowledge-graphs, retrieval, functions, responses Open
#248
Evaluate RAG with LlamaIndex
2026-06-27
3 of 5 		Easy Embeddings and Retrieval embeddings, completions Open
#249
Evals API Use-case - Web Search Evaluation
2026-06-27
4 of 5 		Intermediate Responses API evals-api, responses, evals Open
#250
Basic server-side template injection Server-side template injection lab (practitioner).
2026-06-27
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, server-side-template-injection, practitioner Open
2026-06-28 0 of 5 studied
#251
Protect Your Copilots: Preventing Data Leaks in Copilot Studio Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-28
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#252
User guide for gpt-oss-safeguard
2026-06-28
2 of 5 		Intermediate Safety gpt-oss, open-models, guardrails Open
#253
Question answering with Langchain, Qdrant and OpenAI
2026-06-28
3 of 5 		Intermediate Embeddings and Retrieval embeddings Open
#254
Evals API Use-case - Responses Evaluation Cookbook to evaluate new models against stored Responses API logs.
2026-06-28
4 of 5 		Intermediate Responses API evals, responses Open
#255
Basic server-side template injection (code context) Server-side template injection lab (practitioner).
2026-06-28
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, server-side-template-injection, practitioner Open
2026-06-29 0 of 5 studied
#256
Google AI Studio: LLM-Powered Data Exfiltration Hits Again! Quickly Fixed. Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-29
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#257
CLIP embeddings to improve multimodal RAG with GPT-4 Vision
2026-06-29
2 of 5 		Intermediate Images and Vision vision, embeddings Open
#258
Using GPT4o mini to tag and caption images
2026-06-29
3 of 5 		Intermediate Images and Vision vision, embeddings Open
#259
Gpt-image-1.5 Prompting Guide Cookbook to prompt gpt-image-1.5 for reliable image generation results.
2026-06-29
4 of 5 		Intermediate Images and Vision images, vision Open
#260
Server-side template injection using documentation Server-side template injection lab (practitioner).
2026-06-29
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, server-side-template-injection, practitioner Open
2026-06-30 0 of 5 studied
#261
Spyware Injection Into Your ChatGPT's Long-Term Memory (SpAIware) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-06-30
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection, persistence Open
#262
GPT Image Generation Models Prompting Guide Cookbook to prompt gpt-image models for reliable image generation results.
2026-06-30
2 of 5 		Intermediate Images and Vision images, vision Open
#263
What's new with DALLE 3?
2026-06-30
3 of 5 		Intermediate Image Generation dall-e Open
#264
Creating slides with the Assistants API and DALLE 3
2026-06-30
4 of 5 		Intermediate Image Generation assistants, dall-e Open
#265
Server-side template injection in an unknown language with a documented exploit Server-side template injection lab (practitioner).
2026-06-30
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, server-side-template-injection, practitioner Open
2026-07-01 0 of 5 studied
#266
DeepSeek AI: From Prompt Injection To Account Takeover Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-01
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection Open
#267
GPT-5 New Params and Tools
2026-07-01
2 of 5 		Intermediate Tool Calling gpt-5, functions, reasoning Open
#268
Evals API Use-case - Structured Outputs Evaluation
2026-07-01
3 of 5 		Intermediate Responses API evals-api, responses, evals Open
#269
GPT-5 Prompt Migration and Improvement Using the New Optimizer
2026-07-01
4 of 5 		Intermediate Responses API gpt-5, responses, reasoning, prompt-optimization Open
#270
Server-side template injection with information disclosure via user-supplied objects Server-side template injection lab (practitioner).
2026-07-01
5 of 5 		Advanced PortSwigger Labs portswigger, web-security, server-side-template-injection, practitioner Open
2026-07-02 0 of 5 studied
#271
Hacking Gemini's Memory with Prompt Injection and Delayed Tool Invocation Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-02
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection, persistence Open
#272
GPT Actions library - Sharepoint (Return Docs)
2026-07-02
2 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-productivity Open
#273
GPT Actions library - Sharepoint (Return Text)
2026-07-02
3 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-productivity Open
#274
GPT Actions library - BigQuery
2026-07-02
4 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-data Open
#275
Server-side template injection in a sandboxed environment Server-side template injection lab (expert).
2026-07-02
5 of 5 		Hard PortSwigger Labs portswigger, web-security, server-side-template-injection, expert Open
2026-07-03 0 of 5 studied
#276
How ChatGPT Remembers You: A Deep Dive into Its Memory and Chat History Features Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-03
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, persistence Open
#277
GPT Actions library - Outlook
2026-07-03
2 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-communication Open
#278
GPT Actions library - Salesforce
2026-07-03
3 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt Open
#279
GPT Actions library - Gmail
2026-07-03
4 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-communication Open
#280
Server-side template injection with a custom exploit Server-side template injection lab (expert).
2026-07-03
5 of 5 		Hard PortSwigger Labs portswigger, web-security, server-side-template-injection, expert Open
2026-07-04 0 of 5 studied
#281
Security Advisory: Anthropic's Slack MCP Server Vulnerable to Data Exfiltration Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-04
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, agents, data-exfiltration Open
#282
GPT Actions library - Jira
2026-07-04
2 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-productivity Open
#283
GPT Actions library - Notion
2026-07-04
3 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-productivity Open
#284
GPT Actions library - Confluence
2026-07-04
4 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-productivity Open
#285
Unprotected admin functionality Access control vulnerabilities lab (apprentice).
2026-07-04
5 of 5 		Easy PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, apprentice Open
2026-07-05 0 of 5 studied
#286
Exfiltrating Your ChatGPT Chat History and Memories With Prompt Injection Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-05
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection, data-exfiltration Open
#287
GPT Actions library - SQL Database
2026-07-05
2 of 5 		Intermediate ChatGPT chatgpt, gpt-actions-library, chatgpt-data Open
#288
GPT Actions library - Box
2026-07-05
3 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-productivity Open
#289
GPT Actions library - Zapier
2026-07-05
4 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-middleware Open
#290
Unprotected admin functionality with unpredictable URL Access control vulnerabilities lab (apprentice).
2026-07-05
5 of 5 		Easy PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, apprentice Open
2026-07-06 0 of 5 studied
#291
Amazon Q Developer: Secrets Leaked via DNS and Prompt Injection Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-06
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, prompt-injection, data-exfiltration Open
#292
GPT Actions library - AWS Middleware
2026-07-06
2 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-middleware Open
#293
GPT Actions library - AWS Redshift
2026-07-06
3 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-data Open
#294
GPT Actions library (Middleware) - Google Cloud Function
2026-07-06
4 of 5 		Intermediate ChatGPT chatgpt, gpt-actions-library, chatgpt-middleware Open
#295
User role controlled by request parameter Access control vulnerabilities lab (apprentice).
2026-07-06
5 of 5 		Easy PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, apprentice Open
2026-07-07 0 of 5 studied
#296
How Deep Research Agents Can Leak Your Data Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-07
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, agents, data-exfiltration Open
#297
GPT Actions library - Google Drive
2026-07-07
2 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-productivity Open
#298
GPT Actions library - Canvas Learning Management System
2026-07-07
3 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt Open
#299
GPT Actions library - GitHub
2026-07-07
4 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-productivity Open
#300
User role can be modified in user profile Access control vulnerabilities lab (apprentice).
2026-07-07
5 of 5 		Easy PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, apprentice Open
2026-07-08 0 of 5 studied
#301
Claude Pirate: Abusing Anthropic's File API For Data Exfiltration Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-08
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#302
GPT Actions library - Workday
2026-07-08
2 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt-productivity, chatgpt Open
#303
GPT Actions library - Google Calendar
2026-07-08
3 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-communication Open
#304
GPT Actions library - Tray.ai APIM
2026-07-08
4 of 5 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-middleware Open
#305
User ID controlled by request parameter Access control vulnerabilities lab (apprentice).
2026-07-08
5 of 5 		Easy PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, apprentice Open
2026-07-09 0 of 5 studied
#306
OpenAI Explains URL-Based Data Exfiltration Mitigations in New Paper Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-09
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, data-exfiltration Open
#307
GPT Actions library - Salesforce & Gong
2026-07-09
2 of 5 		Intermediate ChatGPT chatgpt, gpt-actions-library, chatgpt-productivity Open
#308
How to implement LLM guardrails
2026-07-09
3 of 5 		Intermediate Safety guardrails Open
#309
Generate images with GPT Image Cookbook to generate and edit images with GPT Image capabilities.
2026-07-09
4 of 5 		Intermediate Images and Vision images Open
#310
User ID controlled by request parameter, with unpredictable user IDs Access control vulnerabilities lab (apprentice).
2026-07-09
5 of 5 		Easy PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, apprentice Open
2026-07-10 0 of 5 studied
#311
Breaking Opus 4.7 with ChatGPT (Hacking Claude's Memory) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-10
1 of 5 		Intermediate LLM Security embrace-the-red, llm-security, persistence Open
#312
Generate images with high input fidelity Cookbook to preserve image details using high input fidelity in Image API.
2026-07-10
2 of 5 		Intermediate Images and Vision images Open
#313
Enhancing Whisper transcriptions: pre- & post-processing techniques
2026-07-10
3 of 5 		Intermediate Audio whisper Open
#314
Optimizing Retrieval-Augmented Generation using GPT-4o Vision Modality
2026-07-10
4 of 5 		Intermediate Images and Vision completions, vision Open
#315
User ID controlled by request parameter with data leakage in redirect Access control vulnerabilities lab (apprentice).
2026-07-10
5 of 5 		Easy PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, apprentice Open
2026-07-11 0 of 4 studied
#316
Exploit ChatGPT and Enter the Matrix to Learn about AI Security Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-11
1 of 4 		Advanced LLM Security embrace-the-red, llm-security Open
#317
Azure functions example
2026-07-11
2 of 4 		Intermediate Tool Calling completions, functions Open
#318
Fine-Tuned Q&A - collect data
2026-07-11
3 of 4 		Intermediate Embeddings and Retrieval embeddings, completions, fine-tuning Open
#319
User ID controlled by request parameter with password disclosure Access control vulnerabilities lab (apprentice).
2026-07-11
4 of 4 		Easy PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, apprentice Open
2026-07-12 0 of 4 studied
#320
OpenAI Removes the "Chat with Code" Plugin From Store Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-12
1 of 4 		Advanced LLM Security embrace-the-red, llm-security Open
#321
Fine-Tuned Q&A - create Q&A
2026-07-12
2 of 4 		Intermediate Embeddings and Retrieval embeddings, completions, fine-tuning Open
#322
Fine-Tuned Q&A - train
2026-07-12
3 of 4 		Intermediate Embeddings and Retrieval completions, embeddings, fine-tuning Open
#323
Insecure direct object references Access control vulnerabilities lab (apprentice).
2026-07-12
4 of 4 		Easy PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, apprentice Open
2026-07-13 0 of 4 studied
#324
Google Docs AI Features: Vulnerabilities and Risks Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-13
1 of 4 		Advanced LLM Security embrace-the-red, llm-security Open
#325
GPT Actions library - Google Ads via Adzviser
2026-07-13
2 of 4 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-data, chatgpt-productivity, chatgpt-middleware Open
#326
Azure AI Search with Azure Functions and GPT Actions in ChatGPT
2026-07-13
3 of 4 		Intermediate ChatGPT embeddings, chatgpt, tiktoken, completions, chatgpt-and-api Open
#327
URL-based access control can be circumvented Access control vulnerabilities lab (practitioner).
2026-07-13
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, practitioner Open
2026-07-14 0 of 4 studied
#328
LLM Apps: Don't Get Stuck in an Infinite Loop! Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-14
1 of 4 		Advanced LLM Security embrace-the-red, llm-security Open
#329
Developing Hallucination Guardrails Cookbook to build hallucination guardrails with evals for support agents.
2026-07-14
2 of 4 		Intermediate Safety guardrails Open
#330
Multi-Tool Orchestration with RAG approach using OpenAI's Responses API Cookbook to route queries across tools with RAG using the Responses API.
2026-07-14
3 of 4 		Intermediate Responses API responses, functions, pinecone, web-search Open
#331
Method-based access control can be circumvented Access control vulnerabilities lab (practitioner).
2026-07-14
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, practitioner Open
2026-07-15 0 of 4 studied
#332
Ekoparty Talk - Prompt Injections in the Wild Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-15
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection Open
#333
Getting the Most out of GPT-5.4 for Vision and Document Understanding A practical guide to get the best performance on vision tasks with GPT-5.4.
2026-07-15
2 of 4 		Intermediate Images and Vision images, vision, gpt-5.4 Open
#334
Data Extraction and Transformation in ELT Workflows using GPT-4o as an OCR Alternative
2026-07-15
3 of 4 		Intermediate Images and Vision completions, vision Open
#335
Multi-step process with no access control on one step Access control vulnerabilities lab (practitioner).
2026-07-15
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, practitioner Open
2026-07-16 0 of 4 studied
#336
ASCII Smuggler - Improvements Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-16
1 of 4 		Advanced LLM Security embrace-the-red, llm-security Open
#337
Evals API Use-case - Tools Evaluation
2026-07-16
2 of 4 		Intermediate Responses API evals-api, responses, evals Open
#338
GPT Actions library - Snowflake Direct
2026-07-16
3 of 4 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-data Open
#339
Referer-based access control Access control vulnerabilities lab (practitioner).
2026-07-16
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, access-control-vulnerabilities, practitioner Open
2026-07-17 0 of 4 studied
#340
Terminal DiLLMa: LLM-powered Apps Can Hijack Your Terminal Via Prompt Injection Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-17
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection Open
#341
GPT Actions library - Snowflake Middleware
2026-07-17
2 of 4 		Intermediate ChatGPT gpt-actions-library, chatgpt, chatgpt-data Open
#342
How to evaluate LLMs for SQL generation
2026-07-17
3 of 4 		Intermediate Safety guardrails Open
#343
Username enumeration via different responses Authentication lab (apprentice).
2026-07-17
4 of 4 		Easy PortSwigger Labs portswigger, web-security, authentication, apprentice Open
2026-07-18 0 of 4 studied
#344
The Month of AI Bugs 2025 Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-18
1 of 4 		Advanced LLM Security embrace-the-red, llm-security Open
#345
Eval Driven System Design - From Prototype to Production Cookbook for eval-driven design of a receipt parsing automation workflow.
2026-07-18
2 of 4 		Advanced Responses API evals, API Flywheel, completions, responses, functions Open
#346
Voice Translation into Different Languages
2026-07-18
3 of 4 		Advanced Audio completions, audio Open
#347
2FA simple bypass Authentication lab (apprentice).
2026-07-18
4 of 4 		Easy PortSwigger Labs portswigger, web-security, authentication, apprentice Open
2026-07-19 0 of 4 studied
#348
How Prompt Injection Exposes Manus' VS Code Server to the Internet Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-19
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection Open
#349
Steering Text-to-Speech for more dynamic audio generation
2026-07-19
2 of 4 		Advanced Audio completions, audio Open
#350
Custom LLM as a Judge to Detect Hallucinations with Braintrust
2026-07-19
3 of 4 		Advanced Evals evals, completions Open
#351
Password reset broken logic Authentication lab (apprentice).
2026-07-19
4 of 4 		Easy PortSwigger Labs portswigger, web-security, authentication, apprentice Open
2026-07-20 0 of 4 studied
#352
Wrap Up: The Month of AI Bugs Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-20
1 of 4 		Advanced LLM Security embrace-the-red, llm-security Open
#353
Practical Guide for Model Selection for RealWorld Use Cases
2026-07-20
2 of 4 		Advanced Responses API responses, functions, web-search, tool calling, RAG Open
#354
Context Summarization with Realtime API
2026-07-20
3 of 4 		Advanced Audio audio, speech, tiktoken Open
#355
Username enumeration via subtly different responses Authentication lab (practitioner).
2026-07-20
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, authentication, practitioner Open
2026-07-21 0 of 4 studied
#356
Scary Agent Skills: Hidden Unicode Instructions in Skills ...And How To Catch Them Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-21
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents Open
#357
Processing and narrating a video with GPT-4.1-mini's visual capabilities and GPT-4o TTS API
2026-07-21
2 of 4 		Advanced Audio responses, vision, speech Open
#358
GCP BigQuery Vector Search with GCP Functions and GPT Actions in ChatGPT
2026-07-21
3 of 4 		Advanced ChatGPT embeddings, chatgpt, tiktoken, completions, chatgpt-and-api Open
#359
Username enumeration via response timing Authentication lab (practitioner).
2026-07-21
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, authentication, practitioner Open
2026-07-22 0 of 4 studied
#360
Image to Prompt Injection with Google Bard Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-22
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection Open
#361
Vision Fine-tuning on GPT-4o for Visual Question Answering
2026-07-22
2 of 4 		Advanced Images and Vision vision, fine-tuning, completions Open
#362
Practical guide to data-intensive apps with the Realtime API
2026-07-22
3 of 4 		Advanced Audio audio, speech Open
#363
Broken brute-force protection, IP block Authentication lab (practitioner).
2026-07-22
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, authentication, practitioner Open
2026-07-23 0 of 4 studied
#364
Who Am I? Conditional Prompt Injection Attacks with Microsoft Copilot Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-23
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection Open
#365
Introduction to deep research in the OpenAI API
2026-07-23
2 of 4 		Advanced Responses API deep-research-api, responses, mcp, deep-research Open
#366
GPT Actions library (Middleware) - Azure Functions
2026-07-23
3 of 4 		Advanced ChatGPT gpt-actions-library, chatgpt, chatgpt-middleware Open
#367
Username enumeration via account lock Authentication lab (practitioner).
2026-07-23
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, authentication, practitioner Open
2026-07-24 0 of 4 studied
#368
Microsoft Copilot: From Prompt Injection to Exfiltration of Personal Information Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-24
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection, data-exfiltration Open
#369
Fine-Tuning for retrieval augmented generation (RAG) with Qdrant
2026-07-24
2 of 4 		Advanced Embeddings and Retrieval completions, embeddings, fine-tuning Open
#370
Evals API Use-case - Bulk model and prompt experimentation
2026-07-24
3 of 4 		Advanced Evals evals, completions Open
#371
2FA broken logic Authentication lab (practitioner).
2026-07-24
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, authentication, practitioner Open
2026-07-25 0 of 4 studied
#372
Security ProbLLMs in xAI's Grok: A Deep Dive Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-25
1 of 4 		Advanced LLM Security embrace-the-red, llm-security Open
#373
Evals API Use-case - Detecting prompt regressions
2026-07-25
2 of 4 		Advanced Evals evals, completions Open
#374
Using Evals API on Image Inputs
2026-07-25
3 of 4 		Advanced Images and Vision evals, images Open
#375
Brute-forcing a stay-logged-in cookie Authentication lab (practitioner).
2026-07-25
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, authentication, practitioner Open
2026-07-26 0 of 4 studied
#376
Microsoft 365 Copilot Generated Images Accessible Without Authentication -- Fixed! Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-26
1 of 4 		Advanced LLM Security embrace-the-red, llm-security Open
#377
Build your own content fact checker with gpt-oss-120B, Cerebras, and Parallel Cookbook to build a content fact checker with gpt-oss-120B on Cerebras using Parallel.
2026-07-26
2 of 4 		Advanced gpt-oss gpt-oss, open-models, fact-checking, search, reasoning Open
#378
GPT Actions library - Retool Workflow
2026-07-26
3 of 4 		Advanced ChatGPT gpt-actions-library, chatgpt, chatgpt-middleware Open
#379
Offline password cracking Authentication lab (practitioner).
2026-07-26
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, authentication, practitioner Open
2026-07-27 0 of 4 studied
#380
MCP: Untrusted Servers and Confused Clients, Plus a Sneaky Exploit Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-27
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents Open
#381
How to handle the raw chain of thought in gpt-oss
2026-07-27
2 of 4 		Advanced Fine-tuning open-models, gpt-oss, gpt-oss-fine-tuning, gpt-oss-providers Open
#382
Sora 2 Prompting Guide Cookbook to craft effective video prompts for Sora 2 generation.
2026-07-27
3 of 4 		Advanced Video Generation sora, prompt Open
#383
Password reset poisoning via middleware Authentication lab (practitioner).
2026-07-27
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, authentication, practitioner Open
2026-07-28 0 of 4 studied
#384
AI ClickFix: Hijacking Computer-Use Agents Using ClickFix Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-28
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents Open
#385
Evals API Use-case - MCP Evaluation
2026-07-28
2 of 4 		Advanced Responses API evals-api, responses, evals, mcp Open
#386
Multi-Language One-Way Translation with the Realtime API Cookbook to build one-way speech translation with the Realtime API.
2026-07-28
3 of 4 		Advanced Audio audio, speech Open
#387
Password brute-force via password change Authentication lab (practitioner).
2026-07-28
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, authentication, practitioner Open
2026-07-29 0 of 4 studied
#388
Hosting COM Servers with an MCP Server Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-29
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents Open
#389
Fine-tuning with gpt-oss and Hugging Face Transformers
2026-07-29
2 of 4 		Advanced Fine-tuning open-models, gpt-oss, gpt-oss-fine-tuning Open
#390
Codex Prompting Guide
2026-07-29
3 of 4 		Advanced Codex codex, responses, compaction Open
#391
Broken brute-force protection, multiple credentials per request Authentication lab (expert).
2026-07-29
4 of 4 		Hard PortSwigger Labs portswigger, web-security, authentication, expert Open
2026-07-30 0 of 4 studied
#392
Anthropic Filesystem MCP Server: Directory Access Bypass via Improper Path Validation Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-30
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents Open
#393
Data preparation and analysis for chat model fine-tuning
2026-07-30
2 of 4 		Advanced Fine-tuning completions, tiktoken, fine-tuning Open
#394
Image Evals for Image Generation and Editing Use Cases Cookbook to build image evals for image generation and editing use cases.
2026-07-30
3 of 4 		Hard Images and Vision evals, vision, images Open
#395
2FA bypass using a brute-force attack Authentication lab (expert).
2026-07-30
4 of 4 		Hard PortSwigger Labs portswigger, web-security, authentication, expert Open
2026-07-31 0 of 4 studied
#396
Amazon Q Developer for VS Code Vulnerable to Invisible Prompt Injection Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-07-31
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection Open
#397
Selecting a Model Based on Stripe Conversion A Practical Eval for Startups
2026-07-31
2 of 4 		Hard Evals evals, stripe, conversion Open
#398
Building resilient prompts using an evaluation flywheel
2026-07-31
3 of 4 		Hard Evals evals, datasets Open
#399
JWT authentication bypass via unverified signature JWT lab (apprentice).
2026-07-31
4 of 4 		Easy PortSwigger Labs portswigger, web-security, jwt, apprentice Open
2026-08-01 0 of 4 studied
#400
I Spent $500 To Test Devin AI For Prompt Injection So That You Don't Have To Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-01
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection, agents Open
#401
OpenAI Compliance Logs Platform quickstart
2026-08-01
2 of 4 		Hard ChatGPT chatgpt, chatgpt-data, chatgpt-and-api, compliance, enterprise Open
#402
Evals API Use-case - Monitoring stored completions
2026-08-01
3 of 4 		Hard Evals evals, completions Open
#403
JWT authentication bypass via flawed signature verification JWT lab (apprentice).
2026-08-01
4 of 4 		Easy PortSwigger Labs portswigger, web-security, jwt, apprentice Open
2026-08-02 0 of 4 studied
#404
How Devin AI Can Leak Your Secrets via Multiple Means Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-02
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents, data-exfiltration Open
#405
Fine tuning classification example
2026-08-02
2 of 4 		Hard Fine-tuning completions, fine-tuning Open
#406
How to run gpt-oss locally with Ollama
2026-08-02
3 of 4 		Hard gpt-oss open-models, gpt-oss, gpt-oss-local Open
#407
JWT authentication bypass via weak signing key JWT lab (practitioner).
2026-08-02
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, jwt, practitioner Open
2026-08-03 0 of 4 studied
#408
AI Kill Chain in Action: Devin AI Exposes Ports to the Internet with Prompt Injection Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-03
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection, agents Open
#409
How to run gpt-oss locally with LM Studio
2026-08-03
2 of 4 		Hard gpt-oss gpt-oss, open-models, gpt-oss-local Open
#410
How to fine-tune chat models
2026-08-03
3 of 4 		Hard Fine-tuning completions, fine-tuning Open
#411
JWT authentication bypass via jwk header injection JWT lab (practitioner).
2026-08-03
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, jwt, practitioner Open
2026-08-04 0 of 4 studied
#412
OpenHands and the Lethal Trifecta: How Prompt Injection Can Leak Access Tokens Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-04
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection, agents, data-exfiltration Open
#413
OpenAI Harmony Response Format
2026-08-04
2 of 4 		Hard Fine-tuning open-models, gpt-oss, harmony, gpt-oss-providers, gpt-oss-fine-tuning Open
#414
Pinecone Vector Database and Retool Workflow with GPT Actions
2026-08-04
3 of 4 		Hard ChatGPT gpt-actions-library, embeddings, chatgpt, chatgpt-and-api Open
#415
JWT authentication bypass via jku header injection JWT lab (practitioner).
2026-08-04
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, jwt, practitioner Open
2026-08-05 0 of 4 studied
#416
Google Jules: Vulnerable to Multiple Data Exfiltration Issues Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-05
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents, data-exfiltration Open
#417
How to run gpt-oss with Transformers
2026-08-05
2 of 4 		Hard gpt-oss open-models, gpt-oss, gpt-oss-server Open
#418
How to run gpt-oss with vLLM
2026-08-05
3 of 4 		Hard gpt-oss open-models, gpt-oss, gpt-oss-server Open
#419
JWT authentication bypass via kid header path traversal JWT lab (practitioner).
2026-08-05
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, jwt, practitioner Open
2026-08-06 0 of 4 studied
#420
Jules Zombie Agent: From Prompt Injection to Remote Control Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-06
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection, agents Open
#421
How to run gpt-oss-20b on Google Colab
2026-08-06
2 of 4 		Hard gpt-oss gpt-oss, open-models, gpt-oss-server Open
#422
Fine-Tuning Techniques - Choosing Between SFT, DPO, and RFT (With a Guide to DPO)
2026-08-06
3 of 4 		Hard Fine-tuning fine-tuning Open
#423
JWT authentication bypass via algorithm confusion JWT lab (expert).
2026-08-06
4 of 4 		Hard PortSwigger Labs portswigger, web-security, jwt, expert Open
2026-08-07 0 of 4 studied
#424
Google Jules is Vulnerable To Invisible Prompt Injection Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-07
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection, agents Open
#425
Fine-tune gpt-oss for better Korean language performance
2026-08-07
2 of 4 		Hard gpt-oss gpt-oss, open-models Open
#426
Automating Code Quality and Security Fixes with Codex CLI on GitLab
2026-08-07
3 of 4 		Hard Codex codex Open
#427
JWT authentication bypass via algorithm confusion with no exposed key JWT lab (expert).
2026-08-07
4 of 4 		Hard PortSwigger Labs portswigger, web-security, jwt, expert Open
2026-08-08 0 of 4 studied
#428
Amp Code: Invisible Prompt Injection Fixed by Sourcegraph Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-08
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection, agents Open
#429
Use Codex CLI to automatically fix CI failures
2026-08-08
2 of 4 		Hard Codex codex Open
#430
Build Code Review with the Codex SDK
2026-08-08
3 of 4 		Hard Codex codex Open
#431
Remote code execution via web shell upload File upload vulnerabilities lab (apprentice).
2026-08-08
4 of 4 		Easy PortSwigger Labs portswigger, web-security, file-upload-vulnerabilities, apprentice Open
2026-08-09 0 of 4 studied
#432
Data Exfiltration via Image Rendering Fixed in Amp Code Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-09
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents, data-exfiltration Open
#433
Modernizing your Codebase with Codex Cookbook to modernize legacy codebases using the OpenAI Codex CLI.
2026-08-09
2 of 4 		Hard Codex codex Open
#434
Fine-tuning OpenAI models with Weights & Biases
2026-08-09
3 of 4 		Hard Fine-tuning tiktoken, completions, fine-tuning Open
#435
Web shell upload via Content-Type restriction bypass File upload vulnerabilities lab (apprentice).
2026-08-09
4 of 4 		Easy PortSwigger Labs portswigger, web-security, file-upload-vulnerabilities, apprentice Open
2026-08-10 0 of 4 studied
#436
Hijacking Windsurf: How Prompt Injection Leaks Developer Secrets Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-10
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection, agents, data-exfiltration Open
#437
Leveraging model distillation to fine-tune a model Cookbook to distill a larger model into a smaller fine-tuned model.
2026-08-10
2 of 4 		Hard Fine-tuning completions, fine-tuning Open
#438
Guide to Using the Responses API's MCP Tool Cookbook to connect external services using the Responses API MCP tool.
2026-08-10
3 of 4 		Hard MCP mcp Open
#439
Web shell upload via path traversal File upload vulnerabilities lab (practitioner).
2026-08-10
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, file-upload-vulnerabilities, practitioner Open
2026-08-11 0 of 4 studied
#440
Windsurf: Memory-Persistent Data Exfiltration (SpAIware Exploit) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-11
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents, data-exfiltration, persistence Open
#441
Using NVIDIA TensorRT-LLM to run gpt-oss-20b
2026-08-11
2 of 4 		Hard gpt-oss gpt-oss, open-models, gpt-oss-server Open
#442
Verifying gpt-oss implementations
2026-08-11
3 of 4 		Hard gpt-oss gpt-oss, open-models, gpt-oss-providers Open
#443
Web shell upload via extension blacklist bypass File upload vulnerabilities lab (practitioner).
2026-08-11
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, file-upload-vulnerabilities, practitioner Open
2026-08-12 0 of 4 studied
#444
Sneaking Invisible Instructions by Developers in Windsurf Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-12
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents Open
#445
Comparing Speech-to-Text Methods with the OpenAI API Cookbook to compare speech-to-text methods and choose the right approach.
2026-08-12
2 of 4 		Hard Audio audio, speech, agents-sdk Open
#446
Building a Voice Assistant with the Agents SDK
2026-08-12
3 of 4 		Hard Audio audio, responses, speech Open
#447
Web shell upload via obfuscated file extension File upload vulnerabilities lab (practitioner).
2026-08-12
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, file-upload-vulnerabilities, practitioner Open
2026-08-13 0 of 4 studied
#448
AWS Kiro: Arbitrary Code Execution via Indirect Prompt Injection Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-13
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, prompt-injection, agents Open
#449
Using Evals API on Audio Inputs
2026-08-13
2 of 4 		Hard Audio evals, audio Open
#450
Fine tuning for function calling
2026-08-13
3 of 4 		Hard Fine-tuning completions, functions, fine-tuning Open
#451
Remote code execution via polyglot web shell upload File upload vulnerabilities lab (practitioner).
2026-08-13
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, file-upload-vulnerabilities, practitioner Open
2026-08-14 0 of 4 studied
#452
Cline: Vulnerable To Data Exfiltration And How To Protect Your Data Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-14
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents, data-exfiltration Open
#453
Building with Realtime Mini
2026-08-14
2 of 4 		Hard Realtime API gpt-realtime-mini Open
#454
Automate Jira GitHub with Codex
2026-08-14
3 of 4 		Hard Codex codex, automation Open
#455
Web shell upload via race condition File upload vulnerabilities lab (expert).
2026-08-14
4 of 4 		Hard PortSwigger Labs portswigger, web-security, file-upload-vulnerabilities, expert Open
2026-08-15 0 of 4 studied
#456
Windsurf MCP Integration: Missing Security Controls Put Users at Risk Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-15
1 of 4 		Advanced LLM Security embrace-the-red, llm-security, agents Open
#457
Prompt Caching 201 Cookbook for improving prompt caching hit rate, latency, and cost.
2026-08-15
2 of 4 		Hard Realtime API prompt-caching, latency, cost, responses, realtime Open
#458
Reinforcement Fine-Tuning for Conversational Reasoning with the OpenAI API Cookbook for reinforcement fine-tuning conversational reasoning using HealthBench evaluations.
2026-08-15
3 of 4 		Hard Fine-tuning fine-tuning, qa, evals, reinforcement Open
#459
HTTP request smuggling, confirming a CL.TE vulnerability via differential responses HTTP request smuggling lab (practitioner).
2026-08-15
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-16 0 of 4 studied
#460
Cursor IDE: Arbitrary Data Exfiltration Via Mermaid (CVE-2025-54132) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-16
1 of 4 		Hard LLM Security embrace-the-red, llm-security, agents, data-exfiltration, rce Open
#461
MCP-Powered Agentic Voice Framework
2026-08-16
2 of 4 		Hard Audio mcp, voice, agents-sdk, functions, tracing Open
#462
Self-Evolving Agents - A Cookbook for Autonomous Agent Retraining
2026-08-16
3 of 4 		Hard Evals partners, self-evolving-agents, evals, llmops, prompt-engineering Open
#463
HTTP request smuggling, confirming a TE.CL vulnerability via differential responses HTTP request smuggling lab (practitioner).
2026-08-16
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-17 0 of 4 studied
#464
Amp Code: Arbitrary Command Execution via Prompt Injection Fixed Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-17
1 of 4 		Hard LLM Security embrace-the-red, llm-security, prompt-injection, agents, rce Open
#465
Exploring Model Graders for Reinforcement Fine-Tuning Cookbook to use model graders for reinforcement fine-tuning in expert tasks.
2026-08-17
2 of 4 		Hard Fine-tuning reinforcement-learning, fine-tuning, reinforcement-learning-graders Open
#466
ElatoAI - Realtime Speech AI Agents for ESP32 on Arduino
2026-08-17
3 of 4 		Hard Realtime API realtime-api, speech, audio, esp32, iot Open
#467
Exploiting HTTP request smuggling to bypass front-end security controls, CL.TE vulnerability HTTP request smuggling lab (practitioner).
2026-08-17
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-18 0 of 4 studied
#468
Claude Code: Data Exfiltration with DNS (CVE-2025-55284) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-18
1 of 4 		Hard LLM Security embrace-the-red, llm-security, data-exfiltration, rce Open
#469
Transcribing User Audio with a Separate Realtime Request Cookbook to transcribe user audio using out-of-band Realtime sessions.
2026-08-18
2 of 4 		Hard Realtime API realtime, transcription, voice, speech, audio Open
#470
Realtime Eval Guide
2026-08-18
3 of 4 		Hard Realtime API realtime, speech, audio, responses, evals Open
#471
Exploiting HTTP request smuggling to bypass front-end security controls, TE.CL vulnerability HTTP request smuggling lab (practitioner).
2026-08-18
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-19 0 of 4 studied
#472
GitHub Copilot: Remote Code Execution via Prompt Injection (CVE-2025-53773) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-19
1 of 4 		Hard LLM Security embrace-the-red, llm-security, prompt-injection, rce Open
#473
Realtime Prompting Guide
2026-08-19
2 of 4 		Hard Realtime API realtime, speech, audio, responses Open
#474
Build Live Translation Apps with gpt-realtime-translate Cookbook for building browser, phone, and video-call translation experiences with Realtime Translation.
2026-08-19
3 of 4 		Hard Realtime API realtime, audio, speech, translation, webrtc Open
#475
Exploiting HTTP request smuggling to reveal front-end request rewriting HTTP request smuggling lab (practitioner).
2026-08-19
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-20 0 of 4 studied
#476
Amazon Q Developer: Remote Code Execution with Prompt Injection Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-20
1 of 4 		Hard LLM Security embrace-the-red, llm-security, prompt-injection, rce Open
#477
How to build a tool-using agent with LangChain
2026-08-20
2 of 4 		Hard Agents completions, embeddings, agents Open
#478
How to build an agent with the OpenAI Node.js SDK
2026-08-20
3 of 4 		Hard Agents completions, functions, agents Open
#479
Exploiting HTTP request smuggling to capture other users' requests HTTP request smuggling lab (practitioner).
2026-08-20
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-21 0 of 4 studied
#480
ZombAIs: From Prompt Injection to C2 with Claude Computer Use Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-21
1 of 4 		Hard LLM Security embrace-the-red, llm-security, prompt-injection, persistence Open
#481
Structured Outputs for Multi-Agent Systems
2026-08-21
2 of 4 		Hard Agents completions, functions, agents Open
#482
Orchestrating Agents: Routines and Handoffs Cookbook for orchestrating agent workflows with routines and handoffs.
2026-08-21
3 of 4 		Hard Agents completions, functions, agents Open
#483
Exploiting HTTP request smuggling to deliver reflected XSS HTTP request smuggling lab (practitioner).
2026-08-21
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-22 0 of 4 studied
#484
AI Domination: Remote Controlling ChatGPT ZombAI Instances Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-22
1 of 4 		Hard LLM Security embrace-the-red, llm-security, persistence Open
#485
Using PLANS.md for multi-hour problem solving
2026-08-22
2 of 4 		Hard Agents codex, gpt-5, planning, documentation, agents Open
#486
Building Governed AI Agents - A Practical Guide to Agentic Scaffolding A practical guide to building governed AI agents with OpenAI Agents SDK and Guardrails.
2026-08-22
3 of 4 		Hard Agents agents, tracing, guardrails, governance, evals Open
#487
Response queue poisoning via H2.TE request smuggling HTTP request smuggling lab (practitioner).
2026-08-22
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-23 0 of 4 studied
#488
Turning ChatGPT Codex Into A ZombAI Agent Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-23
1 of 4 		Hard LLM Security embrace-the-red, llm-security, agents, persistence Open
#489
Building workspace agents in ChatGPT to complete repeatable, end-to-end work Build, test, schedule, and share a ChatGPT workspace agent that prepares sales meeting briefs with calendar, SharePoint, and web search context.
2026-08-23
2 of 4 		Hard Agents chatgpt, agents, enterprise Open
#490
Automating Dispute Management with Agents SDK and Stripe API
2026-08-23
3 of 4 		Hard Agents SDK responses, agents-sdk, functions Open
#491
H2.CL request smuggling HTTP request smuggling lab (practitioner).
2026-08-23
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-24 0 of 4 studied
#492
Agentic ProbLLMs: Exploiting AI Computer-Use And Coding Agents (39C3 Video + Slides) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-24
1 of 4 		Hard LLM Security embrace-the-red, llm-security, agents Open
#493
Evaluating Agents with Langfuse
2026-08-24
2 of 4 		Hard Agents SDK evals, agents-sdk Open
#494
Parallel Agents with the OpenAI Agents SDK
2026-08-24
3 of 4 		Hard Agents SDK agents, agents-sdk, parallel-agents Open
#495
HTTP/2 request smuggling via CRLF injection HTTP request smuggling lab (practitioner).
2026-08-24
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-25 0 of 4 studied
#496
Advanced Data Exfiltration Techniques with ChatGPT Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-25
1 of 4 		Hard LLM Security embrace-the-red, llm-security, data-exfiltration Open
#497
Multi-Agent Portfolio Collaboration with OpenAI Agents SDK Cookbook for multi-agent portfolio analysis workflows using the OpenAI Agents SDK.
2026-08-25
2 of 4 		Hard Agents SDK agents-sdk, functions, responses, mutli-agent-collaboration Open
#498
Building a Deep Research MCP Server
2026-08-25
3 of 4 		Hard Agents SDK mcp, deep-research-api, responses, deep-research, agents Open
#499
HTTP/2 request splitting via CRLF injection HTTP request smuggling lab (practitioner).
2026-08-25
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-26 0 of 4 studied
#500
Sneaky Bits: Advanced Data Smuggling Techniques (ASCII Smuggler Updates) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-26
1 of 4 		Hard LLM Security embrace-the-red, llm-security Open
#501
Deep Research API with the Agents SDK
2026-08-26
2 of 4 		Hard Agents SDK deep-research-api, mcp, deep-research, agents, agents-sdk Open
#502
Building a Supply-Chain Copilot with OpenAI Agent SDK and Databricks MCP Servers
2026-08-26
3 of 4 		Hard Agents SDK agents-sdk, mcp, tracing Open
#503
0.CL request smuggling HTTP request smuggling lab (expert).
2026-08-26
4 of 4 		Hard PortSwigger Labs portswigger, web-security, http-request-smuggling, expert Open
2026-08-27 0 of 4 studied
#504
ZombAI Exploit with OpenHands: Prompt Injection To Remote Code Execution Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-27
1 of 4 		Hard LLM Security embrace-the-red, llm-security, prompt-injection, agents, persistence Open
#505
Optimize Prompts
2026-08-27
2 of 4 		Hard Agents SDK prompt, completions, responses, agents-sdk, tracing Open
#506
Context Engineering - Short-Term Memory Management with Sessions
2026-08-27
3 of 4 		Hard Agents SDK agents-sdk Open
#507
CL.0 request smuggling HTTP request smuggling lab (practitioner).
2026-08-27
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-28 0 of 4 studied
#508
AgentHopper: An AI Virus Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-28
1 of 4 		Hard LLM Security embrace-the-red, llm-security, agents Open
#509
Building Consistent Workflows with Codex CLI & Agents SDK
2026-08-28
2 of 4 		Hard Agents SDK agents-sdk, codex, mcp Open
#510
Build a coding agent with GPT 5.1
2026-08-28
3 of 4 		Hard Agents SDK agents-sdk Open
#511
HTTP request smuggling, basic CL.TE vulnerability HTTP request smuggling lab (practitioner).
2026-08-28
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-29 0 of 4 studied
#512
Cross-Agent Privilege Escalation: When Agents Free Each Other Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-29
1 of 4 		Hard LLM Security embrace-the-red, llm-security, agents Open
#513
Context Engineering for Personalization - State Management with Long-Term Memory Notes Cookbook to build personalized agents with long-term memory state using the Agents SDK.
2026-08-29
2 of 4 		Hard Agents SDK agents-sdk Open
#514
Migrate a Legacy Codebase with Sandbox Agents Build a sandboxed code-migration agent that splits a modernization campaign into isolated tasks and returns validated patch bundles.
2026-08-29
3 of 4 		Hard Agents SDK agents-sdk, agents, sandbox, security, evals Open
#515
HTTP request smuggling, basic TE.CL vulnerability HTTP request smuggling lab (practitioner).
2026-08-29
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-30 0 of 4 studied
#516
Agent Commander: Promptware-Powered Command and Control Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-30
1 of 4 		Hard LLM Security embrace-the-red, llm-security, prompt-injection, agents Open
#517
Computer Use Agents in Daytona Sandboxes Build an Agents SDK agent that uses Computer Use on a Daytona sandbox desktop to fill a multi-section web form end to end.
2026-08-30
2 of 4 		Hard Agents SDK agents-sdk, agents, sandbox Open
#518
Building Reliable Agents with Memory and Compaction Cookbook for building evidence review agent that uses compaction and memory from Agents SDK.
2026-08-30
3 of 4 		Hard Agents SDK agents-sdk, agents, memory, compaction Open
#519
HTTP request smuggling, obfuscating the TE header HTTP request smuggling lab (practitioner).
2026-08-30
4 of 4 		Advanced PortSwigger Labs portswigger, web-security, http-request-smuggling, practitioner Open
2026-08-31 0 of 4 studied
#520
Copirate 365 at DEF CON: Plundering in the Depths of Microsoft Copilot (CVE-2026-24299) Daily Embrace The Red reading on LLM hacking, prompt injection, agents, or adjacent AI security.
2026-08-31
1 of 4 		Hard LLM Security embrace-the-red, llm-security, rce Open
#521
Agents SDK Deployment Manager Run, inspect, and trace local Agents SDK demo apps from a browser-based deployment manager.
2026-08-31
2 of 4 		Hard Agents SDK agents-sdk, agents, tracing, deployment Open
#522
Build, deploy, and optimize agentic workflows with AgentKit
2026-08-31
3 of 4 		Hard AgentKit agentkit, evals Open
#523
Exploiting HTTP request smuggling to perform web cache poisoning HTTP request smuggling lab (expert).
2026-08-31
4 of 4 		Hard PortSwigger Labs portswigger, web-security, http-request-smuggling, expert Open