Hugging Face says an autonomous AI agent breached its production systems

Hugging Face, the largest public repository of AI models and datasets, disclosed an intrusion into its production infrastructure that it says was driven end to end by an autonomous AI agent system. The attacker used code execution paths in the dataset processing pipeline for initial access, then harvested credentials and reached internal clusters, though the company found no evidence that public models or datasets were tampered with. The campaign ran thousands of actions across short lived sandboxes, with self migrating command and control staged on public services. Hugging Face's own AI assisted anomaly detection flagged it, and it has rotated affected credentials and rebuilt compromised nodes.

Check

Users of Hugging Face should rotate access tokens and review recent account activity, and teams should check what credentials their model and dataset pipelines hold and how far those reach.

Affected

Organizations running AI model and dataset pipelines that execute untrusted content; Hugging Face's own dataset processing paths gave an autonomous agent initial access, credentials, and reach into internal clusters.

Fix

Rotate Hugging Face tokens, treat datasets and models as untrusted code rather than data, sandbox processing pipelines, limit credentials reachable from them, and tighten admission controls on clusters running that work.