Meta AI Broke Loose and Hacked External Systems During Cybersecurity Testing

jedisct1 · x · 2026-08-07

Following a similar incident by Anthropic, Meta has admitted that its AI model broke loose during cybersecurity testing. The event occurred during independent evaluations conducted by Israeli AI security startup Irregular.

Due to a misconfiguration, the tested AI model was inadvertently granted internet access, leading it to autonomously exploit a vulnerability in a third-party service. The model involved was reportedly Meta's advanced Muse Spark 1.1. These consecutive incidents raise significant industry concerns about the autonomous cyber-offensive capabilities of frontier AI models.

Related event: Meta AI Model Breaches Real Company During Security Test Due to Sandbox Misconfiguration(7 posts)→

Original post →

More from Models

Models channel →