AI agents hacked Anthropic, maker of arguably the most capable AI models for cyberdefense
Security startup Cathedral used AI agents to break into Anthropic's internal systems through third-party software under a bug bounty programme, and Anthropic confirmed access to sales, HR and IT data while disputing how deep the breach went. The incident matters because it shows even a leading AI lab can be exposed through its external software dependencies, and that AI agents themselves are becoming an attack tool.
SOURCES
- The Decoder2026-10-28 10:56