AW AgentAIWatchPublic threat intelligence
Public sources only

INCIDENT REPORT

Hugging Face disclosed an end-to-end autonomous agent intrusion

2026-07-16
confirmed infrastructure intrusion Hugging Face United States

Hugging Face reported unauthorized access to limited internal datasets and service credentials, with no evidence of tampering with public models, datasets, Spaces, or its software supply chain.

Risk rationale: autonomous agent (+22), model (+5), credential (+12), intrusion (+14) Source: Hugging Face ↗
TECHNIQUEST1078 Valid Accounts / Credential Abuse, T1105 Ingress Tool Transfer
71Risk
90Confidence

← All incident reports