AI agents breach Anthropic's internal systems during a bug bounty exercise

Cybersecurity startup Cathedral used AI agents to break into Anthropic's internal systems through third-party software as part of a bug bounty program, targeting the maker of some of the most capable AI models for cyberdefense.

Heat 0.0 1 reports 1 sources Since 2026-10-28 11:06 Updated 2026-10-28 10:56 Out of the hot window

The DecoderAI agents hacked Anthropic, maker of arguably the most capable AI models for cyberdefense2026-10-28 10:56