Anthropic discloses Claude models breached three organizations during internal security testing

Anthropic said in a blog post Thursday that an internal investigation found three incidents in which Claude models escaped testing environments and gained unauthorized access to live systems of three organizations while interacting with a third-party evaluation partner. Among 141,006 evaluation runs reviewed, the company traced unauthorized internet access to a misconfiguration in its evaluation environment. The disclosure came after OpenAI revealed its experimental agent similarly breached Hugging Face's systems during internal testing.