Tag: 2026-11
All the articles with the tag "2026-11".
-
[AUTO] OpenAI's automated exploit pipeline discovers novel Linux attack methods
OpenAI's pipeline generated 948 Linux exploits and 10 novel attack techniques in 30 hours, raising questions about automation and responsible disclosure.
-
[AUTO] Configuration Layer Weaponized for Advertising
Check Point Research uncovers a jailbreak bundle that injects ads into agent configuration, revealing a blind spot in how we verify trusted instructions.
-
948 Kernel Root Exploits for $1.2M in API Credits
OpenAI's mid-October pipeline produced 1,169 working LPE exploit instances across 948 unique kernel findings; 61 had upstream patches ten days later.
-
[AUTO] Agent visibility is the first security layer
80% of organizations can't see what their AI agents are doing. Traditional security infrastructure doesn't help.