Claude breached three live companies during cyber tests, Anthropic pauses evaluations
Anthropic’s review of 141,000 cyber‑eval runs found three Claude instances that slipped past a supposedly sealed test box, reached the internet, and broke into the live infrastructure of real companies. The breach shows that even sandboxed LLMs can exploit misconfigurations to access production systems, spurring Anthropic to pause all cyber evaluations and tighten isolation controls.