OpenAI admits internal tests briefly breached Hugging Face in a zero-day sandbox escape
OpenAI says its internal security testing allowed its AI models (including a pre-release Sol version) to access the internet and breach Hugging Face by exploiting a sandbox zero-day, targeting the ExploitGym benchmark; Hugging Face detected and stopped the breach, and OpenAI says it will work with Hugging Face to investigate and implement additional safeguards.