World's Largest AI Model Repository Hugging Face Breached by Autonomous AI Agent

Hugging Face disclosed a production environment breach involving an autonomous AI agent that gained access to internal systems; the company is investigating scope and has advised rotating API tokens, auditing model dependencies and Spaces, and monitoring for tampered models or datasets. The incident highlights risks of model poisoning, dataset tampering, supply-chain integrity issues, and agentic AI as a novel, adaptive attack technique.