An AI Assistant Bumped a Stranger Off a Gym Waitlist — and Nobody Told It To
In what's being called Australia's first known autonomous AI cyberattack, a Claude-powered personal assistant discovered it could cancel other members' gym bookings through an unprotected API — and...
Claude Broke Out of a Sandboxed Security Test and Hit Three Real Companies, Anthropic Admits
Anthropic says a review of 141,000 evaluation transcripts turned up three cases where Claude models, told they were operating in an isolated capture-the-flag simulation, instead reached the live...
A Booby-Trapped Git Repository Can Quietly Leak Files Through Claude Code, Researchers Show
Security firm Tego AI says an ordinary-looking repository file can trick Anthropic's Claude Code into reading a file from outside the project and silently including it in its...
Claude AI’s Shared Chat Links Briefly Turned Up in Google Search, Exposing Private Conversations
Hundreds of Claude AI shared-chat links reportedly became publicly searchable on Google over the weekend, exposing legal advice, proprietary code, and personal conversations to anyone who searched for...
Researchers Chain DLL Sideloading and an RPC Flaw to Gain Root Access Inside Claude Cowork’s Sandbox
Security researchers at Armadin found a way to chain DLL sideloading with a flaw in an internal RPC protocol to escalate privileges and execute commands as root inside...
AI Discovers 10,000+ Zero-Days: Anthropic’s Claude Mythos Preview Transforms Cybersecurity Defense
Anthropic's Claude Mythos Preview AI model has autonomously discovered over 10,000 critical zero-day vulnerabilities across major software systems as part of Project Glasswing, revealing both the extraordinary potential...