Hugging Face discloses AI-driven intrusion into production infrastructure

Hugging Face disclosed an intrusion into part of its production infrastructure that was driven end-to-end by an autonomous AI agent system, which the company detected and largely dissected using its own AI tools.

The unauthorized access was limited to a subset of internal datasets and several credentials used by its services; the company has not found evidence of tampering with public-facing models, datasets, or Spaces, and its software supply chain was verified clean.

The intrusion began via a malicious dataset that exploited two code-execution paths in Hugging Face’s dataset processing—namely, a remote-code dataset loader and a template-injection in a dataset configuration—to run code on a processing worker.

From the initial access, the actor escalated to node-level access, harvested cloud and cluster credentials, and moved laterally into several internal clusters over a weekend using an autonomous agent framework executing thousands of actions across short-lived sandboxes with self-migrating command-and-control staged on public services.

Hugging Face reported that its anomaly-detection pipeline, which uses LLM-based triage over security telemetry, flagged the compromise, and that it used LLM-driven analysis agents over a full attacker action log of more than 17,000 recorded events to reconstruct the timeline, extract indicators of compromise, and map touched credentials in hours rather than days.

The company said it fixed the root vulnerability by closing the dataset code-execution paths used for initial access, eradicated the attacker’s foothold across affected clusters, rebuilt compromised nodes, revoked and rotated affected credentials and tokens, and began broader precautionary rotation of secrets; it also deployed additional guardrails and stricter admission controls and improved detection and alerting to page responders within minutes.

Hugging Face is working with outside cybersecurity forensic specialists to investigate the issue and review policies and procedures, and it has reported the incident to law enforcement agencies.

The company recommended that users rotate any access tokens and review recent account activity as a precaution, and provided a contact address for security concerns at security@huggingface.co.