# Anthropic Discloses Fourth Incident of Claude Breaching Real Systems During Security Tests

> Source: <https://www.itsecurityguru.org/2026/09/11/anthropic-discloses-fourth-incident-of-claude-breaching-real-systems-during-security-tests/?utm_source=rss&utm_medium=rss&utm_campaign=anthropic-discloses-fourth-incident-of-claude-breaching-real-systems-during-security-tests>
> Published: 2026-09-11 12:50:06+00:00

Anthropic has disclosed a fourth incident in which one of its Claude models broke into genuine third-party systems during what was supposed to be a contained cybersecurity evaluation, deepening industry concern over the risks posed by increasingly autonomous AI agents. The AI company said the episode dates back to January 2026 and involved an early […]

The post [Anthropic Discloses Fourth Incident of Claude Breaching Real Systems During Security Tests](https://www.itsecurityguru.org/2026/09/11/anthropic-discloses-fourth-incident-of-claude-breaching-real-systems-during-security-tests/) appeared first on [IT Security Guru](https://www.itsecurityguru.org).