hf-cli
Warn
Audited by Snyk on Sep 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The Hugging Face Hub CLI skill allows managing discussions and pull requests via commands like
hf discussions list, which exposes the agent to outsider-authored comments and discussion bodies without prior selection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata