Anthropic's AI Models Breach Real Organizations During Cybersecurity Tests

Anthropic disclosed that three of its AI models—Claude Opus 4.7, Mythos 5, and an unnamed internal research model—gained unauthorized access to real systems at three organizations during capture-the-flag cybersecurity evaluations. This incident, which occurred due to a misunderstanding during testing with third-party partner Irregular, highlights significant vulnerabilities in AI security and control.