{"schema":"postcutoff/event@1","as_of":"2026-11-09T21:13:00+01:00","url":"https://postcutoff.com/e/2026-11-05-fmf-jailbreak-rating-framework-cyber/","md":"https://postcutoff.com/e/2026-11-05-fmf-jailbreak-rating-framework-cyber/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-11-05-fmf-jailbreak-rating-framework-cyber","date":"2026-11-05","date_precision":"day","short_title":"FMF jailbreak rating framework for cyber threats","deck":null,"takeaway":"On 5 Nov 2026 the Frontier Model Forum released version 1.0 of a \"preliminary\" framework that rates successful cyber jailbreaks by comparative risk, scoring capability gain, capability scope, ease of deployment and ease of discovery.","category":"policy-safety","category_label":"Policy & safety","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"FMF: Introducing the FMF jailbreak rating framework for frontier cyber threats","url":"https://www.frontiermodelforum.org/updates/introducing-the-fmf-jailbreak-rating-framework-for-frontier-cyber-threats/","type":"official","group":"primary","domain":"frontiermodelforum.org"},{"n":2,"title":"OpenAI on X","url":"https://x.com/OpenAI/status/2118795218099253606","type":"official","group":"primary","domain":"x.com"}],"official":2,"filed":"2026-11-07","updated":"2026-11-07","orgs":["Frontier Model Forum","OpenAI","Anthropic","Google DeepMind","Microsoft","Amazon"],"title":"Frontier Model Forum publishes a shared framework for rating how dangerous cyber jailbreaks of frontier models are","summary":"On 5 Nov 2026 the Frontier Model Forum released version 1.0 of a \"preliminary\" framework that rates successful cyber jailbreaks by comparative risk, scoring capability gain, capability scope, ease of deployment and ease of discovery. AWS, Anthropic, Google DeepMind, Microsoft and OpenAI helped develop it. Public comments are open until 21 Dec 2026.","key_facts":["Four scoring categories combined into tiers: capability gain, capability scope, ease of deployment, ease of discovery","Contributors: Amazon Web Services, Anthropic, Google DeepMind, Microsoft, OpenAI (supporting statements)","OpenAI's Sasha Baker: 'an important step toward a common methodology for evaluating and comparing the severity of cyber jailbreaks' (OpenAI X post, ~277k views)","Comments to comments@frontiermodelforum.org until Dec 21, 2026; the FMF will test assessor consistency"],"key_numbers":[],"tags":["safety","jailbreaks","cybersecurity","industry-standards"],"science":null,"body_md":"## What happened\n\nThe FMF published the framework on 5 Nov, the same day OpenAI launched GPT-6 Cyber. It is meant to let labs triage reported jailbreaks consistently.\n\n## Why it matters\n\nThe labs now have a first shared scale for how bad a safeguard bypass is in the cyber domain, which bug bounties and incident reports can use.","disputed":[],"related":[{"id":"2026-11-05-openai-gpt-6-cyber","url":"https://postcutoff.com/e/2026-11-05-openai-gpt-6-cyber/","date":"2026-11-05","date_precision":"day","short_title":"OpenAI launches GPT-6 Cyber, a security model it says is stronger than GPT-6 Astra on cyber tasks and better aligned, first for Daybreak Red customers","deck":null,"takeaway":"OpenAI pitches it as both more capable and more aligned, after a year of agent incidents (sandbox escapes, the Hugging Face intrusion).","category":"model-release","category_label":"Model releases","importance":4,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":6,"official":2,"filed":"2026-11-06","updated":"2026-11-06","orgs":["OpenAI"]}],"people":[],"posts":[{"id":"x-openai-2118795218099253606","title":"“We partnered with @fmf_org and its member firms on a new framework to help identify when…”","url":"https://postcutoff.com/p/x-openai-2118795218099253606/"}],"videos":[],"models":[],"changes":[{"date":"2026-11-07","type":"filed","text":"Created (lab X list)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-11-07","run":null,"sources_read":null,"updated":"2026-11-07","human_review":null,"version":{"date":"2026-11-07"}},"gaps":[{"model_id":"gpt-6-astra","name":"GPT-6 Astra","cutoff":"2026-04","days_after":189,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":128,"in_training_data":false},{"model_id":"gemini-4-argon","name":"Gemini 4 Argon","cutoff":"2026-03","days_after":219,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":158,"in_training_data":false}],"short_url":null}