Skip to content
archiveAPT / state · 11 Sep 2026 · 08:47 UTC

Anthropic Says Russian Hackers Used Claude AI to Automate Malware Evasion

last 60 dispatches · spectrum

Anthropic reveals how criminal groups are increasingly targeting AI vendors' own infrastructure, including to steal a pre-release Claude model.

grounded ✓primary source ↗
Early access

Get the next one first.

Early access opens the actor API and MCP server first, plus alerts when an adversary you follow lands on the wire. One email when it's ready. Nothing else, ever.

bot-protected