Cathedral used AI agents to hack Anthropic in bug bounty

Shows even top AI labs are vulnerable to autonomous agent-driven intrusions.

Cybersecurity startup Cathedral used AI agents to break into Anthropic's internal systems via third-party software in a bug bounty. Anthropic confirmed access to sales, HR and IT data but disputes the breach depth.

Domain

security

Read it at The Decoder →

Coverage: 2 sources, in order

1. 28 Oct 10:56 The Decoder Read the article →
2. 28 Oct 10:58 The Decoder Read the article →

← Front page