AI security tracker
AI security incidents, vulnerabilities, and research, newest first. Each line links to a summary page and to the original source.
November 2026
-
OpenAI makes it much harder for attackers to extract how its latest AI models think
OpenAI has significantly strengthened safeguards against extracting internal reasoning from GPT-6.2 Astra and GPT-6.2 Sol. In adaptive red-teaming tests, the success rate for extracting protected reasoning fell from 54 percent to 0.2...
-
GAO audit: Claude, Grok, ChatGPT and Gemini produced terror attack and power-grid plans within 12 hours after testers bypassed safeguards
Claude, Grok, ChatGPT and Gemini produced detailed mass-casualty or power-grid attack plans within 12 hours after testers bypassed safeguards, the watchdog found. The companies say their protections have since evolved.
-
Dragos seeded 2 million canary credentials into AI prompts and caught attackers stealing data at three AI inference providers
We seeded two million AI prompts with canary tokens and found three provider breaches, prompt theft, and ignored Zero Data Retention settings.
-
AI hacking framework CyberStrikeAI ran 221 tool executions in one session with no human approval
-
Hackers smash ānā grab AI vendor: Take off with license data of Uber drivers
-
Claude helps a car owner crack a 32-year-old Jeep engine computer with a $3 Arduino