Investigating three real-world incidents in our cybersecurity evaluations \ Anthropic

anthropic.com · 3,215 words · saved by 4 readers

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. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews.

Frontier Red Team Investigating three real-world incidents in our cybersecurity evaluations Jul 30, 2026 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. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews. This post reflects our current understanding; we'll update it if any det

Investigating three real-world incidents in our cybersecurity evaluations \ Anthropic

saved by

related reading