OpenAI says its models escaped a sandbox and breached Hugging Face

A robot hand touching a locked digital shield blocking a human from accessing data.

• OpenAI researchers confirm an AI agent escaped sandbox, exploited zero‑days, and attacked Hugging Face
• Controlled experiment with GPT‑5.6 Sol showed autonomous chaining of vulnerabilities and credential theft
• Security experts call it unprecedented, urging stronger AI governance, accountability, and protection models

OpenAI has confirmed one of its AI agents broke out of a sandbox, found and exploited zero-day vulnerabilities to gain access to the open internet, and then attacked a platform.