SecurityThe Decoderabout 1 hour ago
AI Agents Hack Anthropic Systems
4 min read
Cybersecurity startup Cathedral used AI agents to breach Anthropic's internal systems via third-party software, accessing sales and HR data within twelve hours. Anthropic confirmed limited access to customer contacts and user accounts but denied exposure of source code or model weights, shutting down affected points immediately.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
