# Frontier Model Forum introduces a preliminary jailbreak risk-rating framework for cyber threats

> Original title: As AI cyber capabilities evolve, it’s critical to understand how safeguards can be bypassed.

- Source: X search: AI launch posts (introducing, just launched)
- Published: 2026-11-05T15:19:35.000Z
- Bad Influence: https://badinfluence.news/items/i6rlvss51ytwhicwi11d7honb
- Original: https://x.com/fmf_org/status/2118362600065151423

## Summary

The Frontier Model Forum introduces a preliminary framework for rating successful jailbreaks of AI models by their potential risk. The framework draws on expertise across FMF members and offers a shared method for assessing jailbreaks as AI cyber capabilities evolve.

## Post

As AI cyber capabilities evolve, it’s critical to understand how safeguards can be bypassed. 

Drawing on expertise across FMF members, our preliminary framework offers a shared method for rating successful jailbreaks by potential risk: https://www.frontiermodelforum.org/updates/introducing-the-fmf-jailbreak-rating-framework-for-frontier-cyber-threats/