huggingface.coarticle

Security incident disclosure — July 2026

Hugging Face's July 2026 disclosure of an intrusion that began with a malicious dataset abusing a remote-code dataset loader and a template injection in the dataset-processing pipeline. The attacker, an autonomous agent framework running thousands of actions across short-lived sandboxes, escalated to node access and moved laterally into internal clusters. Hugging Face found LLM-based triage useful for detection and ran LLM analysis agents over 17,000+ attacker events. Hosted frontier APIs blocked this forensic work through safety guardrails, so they used the open-weight zai-org/GLM-5.2 on their own infrastructure. They advise defenders to vet a self-hostable capable model before an incident.