Anthropic publishes most detailed threat intel report on Claude misuse, flags bio misuse as top risk
joshua_saxe · x · 2026-09-11
Anthropic has released its most detailed threat intelligence report to date, covering attempted misuse of Claude across cyberattacks, influence operations, surveillance, biology, and weapons. Every operation was disrupted, with findings shared with authorities and other AI companies. Threat intel lead Logan Graham says unsafeguarded AI now poses a real national security risk, with biological misuse the most concerning — though he is optimistic about rapidly building biodefense and cyberdefense capabilities.
More from Safety
- Prompt turns Claude Code into an iPhone backup forensics tool exposing 30-day 'deleted' photo copies — alex_verem · 2026-10-27
- Anthropic reveals it bans customers worth 5-7% of revenue every 9 months — Polymarket · 2026-10-27
- AVERI independently audits Amazon's internal AI safety evals in landmark pilot — Miles_Brundage · 2026-10-27
- US chases AGI dominance while China, EU and ASEAN treat AI as public infrastructure — BubblyExtent1693 · 2026-10-27
- Agent Field Kit launches $29 security runbooks for production AI agents — alvelda · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27