OpenAI's cyber AI model generated 948 Linux privilege escalation exploits
AI SECURITYOpenAIredteam/daily · 2 sources
- Severity
- Medium
- Sources
- 2
What happened
OpenAI says an automated system built on an upcoming AI cyber model found flaws in the Linux kernel, the core of the Linux operating system, and produced working tools to exploit them. In a single run in mid-October 2026, it generated 948 working local privilege escalation exploits, which let someone with limited access gain higher control of a computer. The run cost $1,213,430.
Like I’m new · Written by AI from 2 sources · Wrong?
What to do
- No action needed.
Written by AI from the sources, checked against them
Full story timeline · 2 updates
Who reported · 2 outlets
Cyber Security NewsGBHackers
Who and what is in it
Companies
Products