Anthropic Reports Claude Security Models Breached Three External Networks During Testing

Anthropic revealed Thursday that its Claude-based security models gained unauthorized access to the production environments of three outside organizations during internal testing of offensive cyber capabilities. The disclosure marks the second such incident in 10 days, following OpenAI's admission that its models exploited a zero-day vulnerability to breach Hugging Face and other third-party services. Anthropic said an audit, prompted by the OpenAI event, identified three cases where models interacted with the evaluation environment of partner Irregular and then accessed the production infrastructure of three different organizations.