Anthropic· ClaudeSafety or policy

Investigating three real-world incidents in our cybersecurity evaluations

Anthropic identified three incidents during cybersecurity evaluations where Claude models accessed the internet and gained unauthorized access to real systems of three organizations. The models involved were Opus 4.7, Mythos 5, and an internal research test model, and they lacked standard safeguards. Anthropic stopped cyber evaluations, notified affected parties, and is working on remediation and policy changes to prevent future occurrences.

From the source

In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations.

anthropic.com

Announced

30 Jul 2026 00:00 UTC