AIHugging Face1h ago
A fake OpenAI release snuck onto Hugging Face
Hugging Face publishes a timeline of the OpenAI agent intrusion, including how the agent took ~17.6K actions, and details using GLM-5.2 to analyze the attack
This post walks through how the intrusion actually worked: the two initial-access vectors, how the agent pivoted and moved laterally …
Read full articleSource: Hugging Face · Opens in new tab