THEMETASEC

Cybersecurity News, Aggregated

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

SecurityWeek · 2 hours ago Vuln

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.

Read full story at SecurityWeek →