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

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.

948 flaws, 1,169 working exploits

OpenAI's agents scanned about 2.8 million lines of kernel code, or roughly 7% of the project. “Our prototype identified and analyzed 2,308 candidate Linux kernel findings, dynamically reproduced 1,724 vulnerabilities, and produced 948 local privilege escalation (LPE) exploits that could allow an unprivileged local user to gain root access” OpenAI said.

After grouping exploits by their underlying cause and proposed fix, researchers counted 948 distinct flaws.

The October run cost $1,213,430 in API credits, equivalent to around $1,279 per vulnerability. OpenAI compared that with historical $20,000-to-$70,000 payouts 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. 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 the researchers and outside experts they consulted—not merely existing tricks retrieved from training data.

What happens when hackers get the same tools?

AI companies finding critical bugs are just another proof of how systems are capable of performing advanced cybersecurity research achieving results that previously required significant human expertise.

Last week, Anthropic disclosed that an unreleased version of Claude had discovered and exploited serious vulnerabilities in widely used software, including Chrome and Linux. Some of those exploits could execute malicious code remotely with little or no user interaction.

The economics of this research were already changing before OpenAI's announcement.

Researchers at Vidoc Security reproduced several vulnerability discoveries associated with Anthropic's powerful Mythos AI using publicly accessible models for less than $30 per file.

Those tests showed that finding vulnerabilities was becoming increasingly accessible, although reproducing a flaw is different from developing a reliable exploit capable of compromising a protected system.

OpenAI's latest experiment goes further by automating much of that exploitation process, creating a potential advantage for defenders trying to patch software before criminals can take advantage of the same weaknesses.

The company warned that attackers with limited access to an outdated operating system may increasingly be able to escalate their privileges with AI assistance.

OpenAI is attempting to restrict access to its more capable cybersecurity models through verified security programs. Its Daybreak Red initiative provides approved defenders with access to specialized AI tools for vulnerability research, exploit testing, and mitigation development.