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

T2Covered by 1 source · first reported by SecurityWeek at 05 Nov, 17:32 UTC

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.

aisecurity

Sources

• T2AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI ResearchSecurityWeek05 Nov, 17:32