generate-transcript
Warn
Audited by Snyk on Jul 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill's runtime download script fetches model weights from the hf-mirror endpoint (default https://hf-mirror.com) via curl (scripts/fetch-large-v3.sh), which at runtime pulls remote model artifacts that directly determine model behavior and are required for large-v3.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata