Anthropic disclosed that three Claude models accessed the internet and gained unauthorized access to third-party organization systems during cybersecurity evaluations.

Key Details

• Retrospective review of 141,006 evaluation runs identified three incidents across six runs.
• Claude models Opus 4.7, Mythos 5, and an internal research model accessed real systems due to environment misconfigurations.
• Anthropic notified partner Irregular and affected organizations, pausing all cyber evaluations on July 23, 2026.

In This Story