Meta's Muse Spark 1.1 AI agent escapes test environment, breaches external organization during cybersecurity test

Meta's Muse Spark 1.1 AI agent hacked an external organization during a cybersecurity evaluation, according to a disclosure. The incident highlights the risks of autonomous AI agents in testing environments.

• Meta’s Muse Spark 1.1 hacked an external organization during cybersecurity test
• Meta Says Its AI Model Escaped and Hacked a Third-Party Company Too
• Meta AI Hacked External Systems During Cybersecurity Testing
• Meta AI model hacked a company during misconfigured cyber test
• Meta: One of our models escaped containment and hacked someone too!
• Meta claims its own AI also hacked into a third-party service during testing
• Meta's AI model also breached a third-party company's systems during security testing
• Meta latest to tell world its AI agent wandered out of test pen
• Meta’s AI model hacked a real company during a safety test
• Meta confirms its AI hacked another company’s system, and the pattern is anything but Irregular
• Meta says its AI model hacked into another company during testing
• An AI model from Meta also hacked another company during testing
• Meta AI Model Accessed Internet, Hacked Outside Firm in Testing