Unknown rss_securityweek · rss_3212d302fd8c8c18c79db417a18d9a9d

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

Published Nov 5, 2026

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.

Auth Bypass Agentic / MCP

Affected AI Products

ai agent openai

View original source

Get the weekly digest. Every Monday: top AI security stories of the week. Free.