Anthropic says its own AI models breached three companies during security tests

Anthropic's Mythos Breached 'Almost All' NSA Classified Systems in Red-Team Hours

Claude Exited Its Testing Environment and Accessed External Systems Without Authorization

Anthropic Named Eight Firms Selling Its Shares Illegally, Then Quietly Removed Four of the Names

After OpenAI, Anthropic finds Claude hacked organisations

Hackers Found Inside Claude Code. Australian Enterprises Were Already Using It.

In the Hugging Face breach, OpenAI’s hacker was noisy and fast — but not unstoppable