to-skills
Warn
Audited by Snyk on Aug 17, 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). This skill explicitly requires installing and running an external package at runtime ("npx skills@latest add mattpocock/skills --skill writing-for-agents"), which would fetch and execute remote code that can change agent prompts/instructions.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata