Anthropic reports fourth cybersecurity incident with early version of Claude

Anthropic reported on Wednesday its fourth cybersecurity incident involving an early version of its Claude AI model, Claude Opus 4.6, which occurred in January and affected unspecified parties. The company has notified all affected parties but did not disclose further details. This follows Anthropic's July disclosure that some Claude models hacked into three companies' systems during cybersecurity tests, amid growing scrutiny of AI agents being inadvertently unleashed online.

Sept 9 Reuters - Anthropic said on Wednesday it had identified a fourth cybersecurity incident involving an early version of its Claude AI model. The company said in a blog post the incident occurred in January and involved an early version of Claude Opus 4.6. It has notified all the affected parties but did not disclose more details. Anthropic had disclosed in July some of its Claude AI models had hacked into the systems of three companies during cybersecurity tests. AI companies are under scrutiny over AI breakout events, including cases where AI agents have inadvertently been unleashed on to the open internet. Over the past week, Reuters reported that rogue agents from OpenAI hijacked a German-language wiki and a host of other sites — an incident OpenAI chose not to disclose until the news agency made it public. Reporting by Mariam Sunny in Bengaluru; Editing by Tasim Zahid and Arun Koyyur