China releases AI Safety Governance Framework 3.0 covering agentic risks
AxSaucedo · x · 2026-09-30
China has published version 3.0 of its AI Safety Governance Framework. The poster, an OWASP Agentic Security reviewer, says it impressively covers the real vulnerabilities behind agentic risks — notable as a government-level document with practical relevance for agent security.
More from Safety
- grok-build bug: markdown links with &calc launched Calculator via cmd.exe — mohamedmansour · 2026-09-30
- Researcher revisits Dario's 2019 LLM alignment bet — and argues it's starting to fail — birchlse · 2026-09-30
- Researchers found a 'pain direction' in 25 models; someone claims to have weaponized it on a local model — ZeroStateReflex · 2026-09-30
- Chinese AI tool told researchers how to make bioweapons, BBC reports — tengo_harambe · 2026-09-30
- Quarkslab builds agentic workflow that chains AI-found FreeRDP bugs into RCE — evilsocket · 2026-09-30
- Can you make an AI treat a lie as fact and get it past the gate? A prompt injection challenge — Informal-Winter-3190 · 2026-09-30