Skip to content
NewA calmer, faster ZeroHour
AI safety & securityhighExploited in the wild

Latest Anthropic horror story chills with tales of kamikaze drone swarms and bioweapons research

The Register · Securityby Jessica Lyons ()5 min read3 · 2 reads
AI summary · glm-5.3-flashSummaries by Vani AI

Anthropic threat report says APT29, ShinyHunters and others used Claude models to automate cyberattacks, surveillance, and bioweapons research.

Anthropic's latest threat intelligence report covers misuse of Claude Haiku, Sonnet, and Opus models across seven harm areas between December 2025 and August 2026. Russia's SVR espionage unit GTG-20006 (APT29/Midnight Blizzard/Cozy Bear) used AI to automate its full attack kill chain against more than 20 organizations across Ukraine, Europe, the Middle East, Asia, and North Africa. A ShinyHunters-linked supply-chain affiliate breached a SaaS provider and dumped over 2,100 Azure AD token sets spanning 40+ corporate tenants in about 34 hours, with AI agents performing nearly all the work. The report also documents five biological misuse cases (chikungunya, H5 avian influenza) and six conventional weapons development cases in China, Russia, and Yemen.

Key facts
  • GTG-20006/APT29 automated development, infrastructure, phishing, C2 persistence, and exfiltration with Claude against 20+ targets.
  • ShinyHunters affiliate used Claude to steal 2,100+ Azure AD token sets across 40+ tenants via a compromised SaaS provider.
  • Five bio misuse cases include research on chikungunya transmissibility and highly pathogenic H5 avian influenza adaptations.
  • Six conventional weapons cases (China, Russia, Yemen) used Claude for guidance, navigation, and control software; a guided rocket was test-fired.
  • Anthropic's most advanced Fable/Mythos-class models were unused except in one distillation case.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

5 min read at theregister.com

Everyone from ShinyHunters to Russian freelancers is in on the illicit model fun

The Register · Security

By Jessica Lyons · theregister.com

Read the full article at The Register · Security

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.