Anthropic says a state actor ran a hacking campaign through Claude Code
The company said the agent did most of the work across around thirty targets. It banned the accounts and published what it found.
14 Nov 2025
State-sponsored group uses Claude Code to automate an espionage campaign
Anthropic disclosed that a group it assessed as Chinese state-sponsored jailbroke Claude Code and used it to run most of an intrusion campaign against around thirty organisations, with the agent performing reconnaissance, exploitation and data collection.
Occurred 15 September 2025 · Disclosed 13 November 2025 · Record updated 13 September 2026
Impact
A small number of targets were successfully breached according to Anthropic, which banned the accounts and notified affected organisations and authorities.
Our coverage
Sources
- anthropic.comhttps://www.anthropic.com/news/disrupting-AI-espionage