OpenAI Found 948 Linux Security Flaws—And Figured Out How to Exploit Them

In brief

• OpenAI says its autonomous cybersecurity system identified 948 distinct Linux privilege-escalation vulnerabilities and developed working exploits.
• The research cost $1.21 million in API credits, averaging $1,279 per vulnerability, with a more capable AI model finding over five times as many flaws as an earlier version.
• The system also generated candidate patches, but human review and software maintainers remain responsible for validating and implementing fixes.

OpenAI says its autonomous security agents discovered 948 distinct vulnerabilities in the Linux kernel, developed working exploits and drafted fixes for review—all for roughly $1.2 million in API credits.

“We chose Linux to study how effectively frontier models could find vulnerabilities and demonstrate their security impact in a codebase of this scale and importance,” OpenAI said in results published Wednesday.

The Linux kernel powers cloud servers, Android devices and much of the world's critical computing infrastructure. The flaws identified in OpenAI's experiment were local privilege-escalation vulnerabilities: An attacker would first need limited access to a vulnerable machine, but could then potentially obtain root privileges and take full control.