cd /news/ai-safety/openai-s-gpt-6-cyber-finds-81-firefo… · home › topics › ai-safety › article
[ARTICLE · art-172058] src=openai.com ↗ pub= topic=ai-safety verified=true sentiment=· neutral

OpenAI's GPT-6 Cyber finds 81 Firefox flaws and exploits 948 Linux bugs

OpenAI released GPT-6 Cyber, a model it classifies as Critical under its Preparedness Framework, after it scored 48.5% on ExploitGym versus 32.1% for GPT-5.6 Cyber. In vulnerability research campaigns, GPT-6 Cyber produced reproducible evidence for 81 previously unknown Firefox vulnerabilities that Mozilla rated high severity, reproduced 1,724 Linux kernel vulnerabilities and built working exploits for 948 of them — more than five times the 166 managed by GPT-5.6 Sol with the same harness — and OpenAI disclosed 304 critical Linux findings with candidate patches to maintainers. OpenAI also said GPT-6 Cyber stayed within task boundaries in 99.93% of honeypot tests without a deployment prompt and 100% with one, up from 94.49% for the previous model.

recommendation

Benchmark offensive-security models on reproducible exploit evidence and honeypot task-boundary rates before deployment; GPT-6 Cyber hit 99.93% boundary compliance without a deployment prompt versus 94.49% for its predecessor.

more in playbook: Evals and testing for LLM apps
read1 min views13 publishedNov 5, 2026

OpenAI released GPT-6 Cyber, a model it classifies as Critical under its Preparedness Framework, after it scored 48.5% on ExploitGym versus 32.1% for GPT-5.6 Cyber. In vulnerability research campaigns it produced reproducible evidence for 81 previously unknown Firefox vulnerabilities that Mozilla rated high severity, and it reproduced 1,724 Linux kernel vulnerabilities and built working exploits for 948 of them, more than five times the 166 managed by GPT-5.6 Sol with the same harness. OpenAI disclosed 304 critical Linux findings with candidate patches to maintainers. The company also said the model stayed within task boundaries in 99.93% of honeypot tests without a deployment prompt and 100% with one, up from 94.49% for the previous model.

── more in #ai-safety 4 stories · sorted by recency
── more on @openai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/openai-s-gpt-6-cyber…] indexed:0 read:1min 2026-11-05 · —