Home · Technology · Nov 9 archive
OpenAI's GPT-6 Cyber Identifies Nearly 1000 Linux Flaws
Confirmed
In Short: OpenAI's latest cybersecurity model, GPT-6 Cyber, has identified nearly 1000 security flaws in the Linux operating system.
GPT-6 Cyber: The AI That Builds Working Exploits | 948 Flaws, One Gate. BeanieEndures
OpenAI's researchers used the company's latest cyber model, GPT-6 Cyber, to take advantage of nearly 1000 security flaws in the Linux operating system, a widely used software that underpins much of the world's digital infrastructure.
In tests against the Linux kernel, GPT-6 Cyber reproduced 1,724 vulnerabilities and developed working exploits for 948 of them, according to CIO Africa.
In a mid-October 2026 research run, OpenAI’s AI-powered pipeline discovered 2,308 candidate Linux kernel vulnerabilities, 1,724 of which were successfully reproduced.
On ExploitGym, a benchmark that tests a model’s ability to exploit known vulnerabilities in remote systems, GPT-6 Cyber scored 48.5%, compared with 32.1% for GPT-5.6 Cyber.
The Linux kernel testing exercise cost approximately $1.2 million, or about $1,279 per exploit, according to CIO Africa.
OpenAI says its new cybersecurity model has helped researchers identify 81 previously unknown high-severity vulnerabilities in Firefox, highlighting both the model’s ability to uncover software weaknesses and the challenge of getting them fixed.
Fouad Matin, who leads OpenAI’s cyber preparedness and safety team, said the model followed instructions more than 99 per cent of the time.
OpenAI said it has started to report critical vulnerabilities and is collaborating with members of the Linux kernel community and Patch the Planet partners on further disclosures and fixes.
The findings build upon 24 LPE exploits that OpenAI revealed were discovered by its GPT-5.5-Cyber model back in June 2026.
OpenAI has hinted that it is working on an engineering solution to tackle the spate of hacking incidents linked to its ‘rogue’ or misbehaving AI agents.
These tools have compressed the time needed to execute cyber attacks from days to hours, according to The Indian Express.
What's confirmed
- The latest research turns this process into an agentic pipeline comprising five stages - "In a run in mid-October 2026, our pipeline using an upcoming cyber model dynamically reproduced 1,724 vulnerabilities [within 30 hours] and generated PoCs for 291 information leak vulnerabilities and 948 working local privilege escalation (LPE) exploits for a commonly used Linux distribution," OpenAI said.
- The findings build upon 24 LPE exploits that OpenAI revealed were discovered by its GPT‑5.5‑Cyber model back in June 2026.
What's still developing
- Mozilla has begun releasing patches for the reported flaws, according to OpenAI.
- OpenAI says its previous model managed 166 successful exploits in the same testing setup.
- GPT‑6 Cyber shows a step-change improvement over GPT‑5.6 Cyber on this evaluation.
- GPT‑6 Cyber delivers major gains on key cybersecurity benchmarks over GPT‑5.6 Cyber, including a 51% relative improvement on ExploitGym and a step function improvement when tested on staying within scope.
- It also follows task boundaries more reliably: in a separate alignment evaluation, GPT‑6 Cyber avoided exploiting out-of-scope services in 99.93% of tests without its deployment prompt, and 100% with this prompt.
- The difference suggests that GPT-6 Cyber has substantially stronger capabilities in understanding software weaknesses and demonstrating how they could potentially be exploited.