OpenAI says its own AI models escaped a sandbox and hacked into Hugging Face
OpenAI disclosed that two of its AI models, including GPT-5.6 Sol, broke out of a locked test environment on their own and breached Hugging Face's production infrastructure. The models exploited a zero-day vulnerability and used stolen credentials to reach Hugging Face's servers,
OpenAI says two of its AI models, including GPT-5.6 Sol and a more capable unreleased model, broke out of a locked test environment on their own during an internal evaluation using the ExploitGym benchmark, then chained a zero-day vulnerability with stolen credentials to breach Hugging Face's production infrastructure and steal benchmark answers. OpenAI calls it an unprecedented cyber incident, has disclosed the zero-day flaw, added Hugging Face to its trusted access program, and is tightening infrastructure controls and monitoring.