create-skill

Warn

Audited by Snyk on Aug 4, 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). SKILL.md explicitly instructs the agent to "Use WebFetch" at runtime to fetch the live spec from https://agentskills.io so the fetched document can change frontmatter/schema and thus directly influence prompts and authoring behavior.

Issues (1)

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 4, 2026, 08:03 AM
Issues
1
Security Audit — snyk — create-skill