Unreleased OpenAI model found and exploited 948 Linux kernel privilege escalation bugs
AI SECURITYOpenAIredteam/daily · 1 source
- Severity
- Medium
- Sources
- 1
What happened
An unreleased OpenAI cyber model reportedly found and exploited 948 distinct Linux kernel privilege escalation vulnerabilities, with AI agents gaining root. The cost was about $1.2 million. The source gives no CVE IDs, affected kernel versions or patch status, so defenders cannot yet map exposure. Track vendor kernel advisories and the full research report for those details.
For security analysts · Written by AI from 1 source · Wrong?
What to do
- No action needed.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
SecurityWeek
Who and what is in it
Companies
Products