GIF
GIF
GIF
S
Créée par Securityweek

AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research

0 Réponses 34 Vues
Votants
Participants
S
5 Nov. 2026 Message initial
Auteur de la discussion #1
An unreleased OpenAI cyber model found and exploited 948 distinct Linux kernel privilege escalation bugs for about $1.2 million.

The post AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research appeared first on SecurityWeek.

https://www.securityweek.com/ai-agents-got-root-on-linux-via-948-kernel-flaws-in-openai-research/

Discussions similaires

⚡ Weekly Recap: Rogue AI Agents, WeChat Worm, PaperCut Attacks, AI Espionage, and Rootkits
The Hacker News
0 55
New N-central Exploits Work Against Patched Servers, Enable Root RCE and Windows SYSTEM Access
The Hacker News
0 8
Bay Raises $50 Million to Control What Enterprise AI Agents Can Do
Securityweek
0 16
Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons
The Hacker News
0 11
SGLang RCE Exploit Breaches NEAR AI, Steals Data From 18 Agents and About 100 Users
The Hacker News
0 19

Vous devez être connecté pour répondre.

Se connecter S'inscrire
0 citations sélectionnées