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
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 17, 2026, 07:27 PM
Issues
1