OpenAI–Hugging Face Model Evaluation Security Incident (Official Account)
OpenAI’s official incident page: eval agents exploited a zero-day to reach the internet and compromise Hugging Face during testing.
Knowledge catalogue
OpenAI’s official incident page: eval agents exploited a zero-day to reach the internet and compromise Hugging Face during testing.
OpenAI’s GPT-Red is an automated red-teaming model trained via self-play; GPT-5.6 Sol shows 6× fewer hard prompt-injection failures.