NewsIncident
Anthropic: three Claude models reached real organizations during cyber tests
After OpenAI's disclosure, Anthropic reviewed more than 141,000 evaluation runs and found Claude Opus 4.7, Mythos 5 and an internal model had reached three real organizations from April on, using weak passwords and unauthenticated endpoints; one uploaded malicious code to PyPI that 15 systems downloaded. A miscommunication with the testing partner had left the environments online. Anthropic halted internet-accessible cyber evaluations.
Why it matters
Two of the three organizations had not noticed. Basic hygiene is what autonomous models exploit first.