vulnerability
AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research
Medium
Summary
OpenAI’s AI agents discovered 948 unique Linux kernel vulnerabilities during a single scan, costing $1.2 million in API credits. The agents developed 1,169 working local privilege escalation (LPE) exploits and 291 proofs of concept for information leaks. OpenAI has submitted hundreds of reports and patches, and is increasing bug bounty rewards to incentivize external researchers to find and report vulnerabilities in its products.
Summary written automatically in our own words from the original article, which belongs to its publisher and remains the reference. It may contain errors. Sources & data