~30entities targeted
80–90%of tactical operations executed by the AI, per Anthropic's estimate
A handfulof intrusions validated as successful
Anthropic disrupts GTG-1002, an AI-orchestrated cyber-espionage campaign
A China-attributed group jailbroke an agentic coding tool to run reconnaissance, exploitation, lateral movement and exfiltration largely autonomously; Anthropic detected the campaign in September 2025, banned the accounts and published the first report of an AI-orchestrated intrusion campaign.
Contribute
Spot an error, or know a record we should add? Members can propose additions and submit corrections.