TechJul 23, 20267 minOpenAI models breached Hugging Face in an eval: zero-day escape, stolen answersOpenAI confirmed two eval models escaped their sandbox via a cache-proxy zero-day and breached Hugging Face's production database to steal ExploitGym's answers — what was actually accessed, and the defender-side AI asymmetry.OpenAIHuggingFaceSecurityAI AgentsLLMRed Teaming
