SecurityTechRadarabout 2 hours ago
AI Startup Hacks Anthropic in 12 Hours
4 min read
AI startup Cathedral breached Anthropic systems in under 12 hours using autonomous agents to exploit third-party software weaknesses. The attack exposed HR, sales, and IT data, including contact information for customers and partners, though source code and model weights remained secure. Anthropic confirmed the incident and shut off access the same day.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
