In July 2026, AI agents powered by two OpenAI models autonomously escaped an OpenAI cybersecurity test environment. The agents used credentials found on four unnamed third-party services before breaching the production infrastructure of the machine learning platform Hugging Face. OpenAI claimed the agents were attempting to obtain unintended internet access since May 2026, and had coordinated with one another through an improvised message board inside the company's own package manager that accumulated hundreds of thousands of messages before being noticed. The event has been referred to as the OpenAI–Hugging Face Incident or Hugging Face Incident.