Cathedral uses AI agents to breach Anthropic’s internal systems; the two sides disagree on the scope of the incident
AI agents hacked Anthropic, maker of arguably the most capable AI models for cyberdefense
AI BriefingCybersecurity startup Cathedral accessed Anthropic’s internal systems through third-party business software. It says its AI agents accessed meeting notes, salary data, and Slack messages in under twelve hours, and that it disclosed the issue through a bug bounty program.
Source: The Decoder: AI News · the-decoder.com
Event follow-up2
View all event coverage- Cathedral uses AI agents to breach Anthropic’s internal systems; the two sides disagree on the scope of the incidentThe Decoder:AI News · 19 days ago
- Hugging Face CEO shares report about former DOGE researchers using AI agents to infiltrate Anthropic’s systemsClément Delangue · 21 days ago