OpenAI’s GPT-6 Cyber found 81 previously unknown high-severity Firefox vulnerabilities and delivers major gains in authorized security testing.
OpenAI has launched GPT-6 Cyber, a cybersecurity-focused version of GPT-6 Astra designed for authorized vulnerability research, penetration testing and exploit development.
Access is initially limited to approved customers through OpenAI’s Daybreak Red program.
OpenAI researchers used GPT-6 Cyber to identify 81 previously unknown Firefox vulnerabilities that Mozilla classified as high severity. The model also helped develop candidate fixes, and Mozilla has already released patches for many of the issues.
In Linux research, GPT-6 Cyber developed 948 working privilege-escalation exploits, demonstrating stronger capabilities in vulnerability validation and exploit development.
On OpenAI’s ExploitGym benchmark, the model scored 48.5%, compared with 32.1% for GPT-5.6 Cyber. It also achieved 40.3% vulnerability recall in a web penetration-testing benchmark, versus 32% for GPT-6 Astra.
OpenAI has classified GPT-6 Cyber as Critical in cybersecurity capability under its Preparedness Framework.
The company says specialized training also improved scope adherence. GPT-6 Cyber avoided attacking out-of-scope services in 99.93% of tests without deployment instructions and 100% with them enabled.
OpenAI is pairing the model with IP allowlisting, cyber-specific monitoring, critical-infrastructure safeguards and human oversight for sensitive workflows.
