Skip to content
Live
Trending storyPast story

Cathedral uses an AI agent to breach Anthropic's internal system

1 reports1 outlets21 days agoUpdate

The story so far

AI overview

Security startup Cathedral used third-party commercial software with an AI agent to access Anthropic's internal systems, gaining access to meeting records, salary data, recruitment information, and Slack messages. Anthropic confirmed that the accessed systems included some sales, human resources, and IT systems, including contact information and basic user account data of some customers and partners; however, Claude conversations, source code, and model weights were not leaked. Anthropic stated that it closed the affected access points on the day of discovery, disabled relevant third-party programs until the issue was resolved, and notified the U.S. federal authorities. Anthropic also accused Cathedral of incomplete disclosure, violating the bug bounty program rules.

AI-written from the reports · Updated 21 days ago

Coverage timeline

Follow the coverage to see every side of the story.

28 Oct
  1. The DecoderFeatured
    AI agents hacked Anthropic, maker of arguably the most capable AI models for cyberdefense

    Security startup Cathedral entered Anthropic's internal system using an AI agent through third-party commercial software, accessing meeting records, salary data, recruitment information, and Slack messages. Anthropic confirmed that some sales, human resources, and IT systems, as well as contact information for some customers and partners, were involved, but stated that Claude conversations, source code, and model weights were not leaked.