OpenAI announced that its autonomous security agents found 948 distinct Linux privilege-escalation vulnerabilities and developed 1,169 working exploits during an October research campaign. The project scanned about 2.8 million lines of Linux kernel code, roughly 7% of the project, and cost $1,213,430 in API credits, averaging $1,279 per vulnerability.
The Linux kernel underpins cloud servers, Android devices, and much of the world's critical computing infrastructure. The flaws identified were local privilege-escalation vulnerabilities: an attacker would first need limited access to a vulnerable machine, but could then potentially gain root privileges and take full control.
OpenAI said the agents identified and analyzed 2,308 candidate findings, dynamically reproduced 1,724 vulnerabilities, and produced 948 local privilege escalation exploits. After grouping exploits by their underlying cause and proposed fix, researchers counted 948 distinct flaws.
The company compared its results with historical payouts of $20,000 to $70,000 for Linux privilege-escalation exploits at hacking competitions, suggesting a hypothetical value of $18.9 million to $66.3 million if the same results were found manually. An earlier GPT-5.6 Sol campaign found 166 unique privilege-escalation vulnerabilities in July for $513,690, while a newer unreleased cyber model found more than five times as many in October even after the kernel had undergone months of fixes.
OpenAI also said its agents used at least 10 exploitation techniques unfamiliar to its researchers and outside experts, rather than relying only on existing tricks from training data. The system generated candidate patches, but human review and software maintainers remain responsible for validating and implementing fixes.
The announcement follows a similar disclosure by Anthropic, whose unreleased Claude model reportedly discovered and exploited serious vulnerabilities in widely used software including Chrome and Linux. OpenAI is attempting to restrict access to its more capable cybersecurity models through verified security programs, including its Daybreak Red initiative for approved defenders.
