skill-picker
Warn
Audited by Snyk on Nov 5, 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). The workflow allows installing and reading third-party agent skills from GitHub repositories (via
skills add/gh api), which can contain outsider-authored free text.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch remote packages and repositories via
npx skills addandgh apifrom arbitrary user-specified or catalog-derived remote sources without enforcing verified digests or cryptographic integrity.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata