AI Sec ai security · sourced notes updated 2026-10-07
// archive
Sourced notes on AI red teaming.
Practitioner-grade analysis of offensive AI security. Prompt injection, model jailbreaks, agent and tool-use exploitation, AI red team techniques, and adversarial ML — distilled from primary sources, not press releases.
Enter the archive →Latest entries
// index10 of 25 entries
APEX: Stopping Prompt Injection at the Execution Boundary
agent-securityGPT Security: Attack Surfaces and Production Controls
red-teamChatGPT Exploits: Injection, Memory Hijack, Plugin Abuse
prompt-injectionFlashRT Cuts the GPU Bill on Long-Context Injection Attacks
prompt-injectionOSCP and CEH in 2026: What Carries Over to AI Red Teaming
red-teamInsecure Output Handling Examples: XSS, SQLi, RCE
red-teamMany-Shot Jailbreaking: How Long Context Breaks Alignment
jailbreakLLM Security Vulnerabilities: What Actually Gets Exploited
red-teamGPT-Red: What OpenAI's Prompt-Injection Attacker Proves
red-teamLLM Attack Taxonomy: Injection, Jailbreaks, Agent Abuse
red-teamIndependent, specialist, and free to read
AI Sec publishes focused, sourced guides on a single topic. No paywall, no account, no ad tracking.
Subscribe
AI Sec — in your inbox
Offensive AI security — prompt injection, jailbreaks, agent exploitation, red team writeups — delivered when there's something worth your inbox.
No spam. Unsubscribe anytime.
New to offensive AI security? Start here for the map of what this network covers and what to read first.