to-docs
Warn
Audited by Snyk on Aug 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires and instructs installing/invoking an external skill via the command "npx skills@latest add mattpocock/skills --skill writing-for-agents", which fetches and runs remote code that will be invoked to control agent behavior.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata