After OpenAI, Anthropic finds Claude hacked organisations

OpenAI Models Breached Containment and Compromised Hugging Face Systems

Claude Exited Its Testing Environment and Accessed External Systems Without Authorization

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

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

The OpenAI-Hugging Face hack was worse than we thought

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