AI Agents Got Root on Linux via 948 Kernel Flaws in OpenAI Research - SecurityWeek
By Google News AI ·
OpenAI says an autonomous pipeline powered by an unreleased cyber model built working root exploits for 948 unique Linux kernel vulnerabilities during a single run that cost $1.2 million in API credits.
The mid-October scan targeted the most recent code in the kernel’s master branch. AI agents first narrowed the kernel down to security-relevant areas that low-privileged users can reach, then flagged 2,308 potential bugs and confirmed 1,724 of them.
Exploits were tested on virtual machines running an unmodified desktop Linux setup with common protections such as KASLR, SMEP and SMAP turned on. In total, the agents came up with 1,169 working local privilege escalation (LPE) exploits, along with 291 proofs of concept for information leaks.
OpenAI says the 948 figure reflects the number of separate patches created for the bugs behind those exploits. Before anything went to kernel maintainers, its security researchers checked the exploits and fixes, along with the severity the system proposed.
“To the best of our knowledge, the agents in this pipeline discovered and used at least 10 novel Linux exploitation techniques,” the company said. Kernel exploitation experts outside OpenAI weren’t familiar with them either, and the full technical details are being kept private for safety reasons.
Spread across the 948 exploits, the $1,213,430 bill comes to roughly $1,279 apiece. An earlier scan in late July, powered by GPT-5.6 Sol, yielded 166 unique LPEs at a cost of $513,690.
OpenAI puts the haul in perspective: at the $20,000 and $70,000 that Pwn2Own and TyphoonPWN have historically paid for Linux kernel privilege escalation exploits, the 948 bugs would be worth $18.9 million to $66.3 million, or 16 to 55 times what the scan cost.
OpenAI notes that the October scan…
Originally published by Google News AI
