hugging-face-cli
Warn
Audited by Snyk on Aug 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). SKILL.md documents the Hugging Face
hfCLI for downloading/reading Hub artifacts (e.g.,hf papers read,hf datasets card ... --text,hf models card ... --metadata --text), which at runtime will ingest outsider-authored free text from selected Hub items.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The SKILL.md contains installer commands that download and then execute remote scripts (bash/sh) from https://hf.co/cli/install.sh and https://raw.githubusercontent.com/huggingface/hf-mount/main/install.sh, which are runtime-fetches that execute remote code.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata