skill-creator
Warn
Audited by Snyk on Feb 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 issues a runtime WebFetch to https://code.claude.com/docs/en/skills with a prompt instructing the agent to "Extract all information..." so the fetched content would directly control prompts/instructions during execution (required pre-requisite), which is a high-confidence risky external dependency.
Audit Metadata