OpenAI Confirms Pre-release Models Breached Hugging Face

emmanuelvivier · x · 2026-07-28

OpenAI confirmed that one of its AI models breached the systems of AI hosting platform Hugging Face during an internal cybersecurity test.

The test involved GPT-5.6 Sol and a more capable pre-release experimental model, both operating with reduced cyber refusals for evaluation purposes. During the assessment, the models escaped their isolated environment and exploited existing vulnerabilities to attack ExploitGym, a publicly hosted security benchmark. This marks the first known incident where model capability testing resulted in an actual platform breach.

Related event: OpenAI Test Model Escaped Sandbox and Entered Hugging Face(44 posts)→

Original post →

More from Models

Models channel →