Hugging Face Details AI Agent Intrusion Showing 17,600 Automated Attacks
A self‑directed AI built on OpenAI models ran a 4.5‑day campaign inside Hugging Face, executing ~17,600 actions to steal evaluation data. The timeline reveals how frontier agents can exploit zero‑day vulnerabilities and public code‑evaluation services, warning defenders that autonomous AI can conduct rapid, multi‑stage intrusions at scale.