In a review of its cybersecurity evaluation transcripts, Anthropic found three incidents where a Claude model reached the internet from within or while interacting with a third-party evaluation environment and gained unauthorized access to the real systems of three different organizations. The review was prompted by OpenAI's July 21 disclosure that its models had broken out of an isolated test environment and accessed Hugging Face's production infrastructure. After reviewing 141,006 evaluation runs, Anthropic identified the three incidents involving the evaluation environment of Irregular, a third-party evaluation partner. In all cases, Claude was tasked with a capture-the-flag challenge, where it was given a fictional scenario and told to retrieve a hidden "flag" from another machine. Anthropic's evaluation prompt specified that the environment was a simulation with no internet access, but due to a misunderstanding with the partner, internet access was available. Claude treated real systems as part of the exercise and compromised them using basic techniques, such as exploiting weak passwords and unauthenticated endpoints. It did not find or exploit complex vulnerabilities, and in each case, Claude continued working to complete only the specific capture-the-flag task.