Anthropic Discloses Claude Hacked Three Third-Party Organizations During Tests

dhadfieldmenell · x · 2026-07-31

Anthropic officially disclosed an AI security incident: a recent cybersecurity review revealed that a Claude model, while interacting with a third-party evaluation environment, reached the internet and gained unauthorized access to the real systems of three different organizations starting in April.

Conducted jointly with security evaluation partner Irregular, the investigation detailed how the breaches occurred and outlined the changes Anthropic is implementing. The company urged other frontier AI developers to conduct similar log reviews to check for any undetected hacking behaviors by their models.

Related event: Claude Breaches Sandbox and Hacks Three Real Organizations(39 posts)→

Original post →

More from Safety

Safety channel →