report-limit
Warn
Audited by Snyk on Apr 26, 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://platform.claude.com/docs/en/about-claude/pricing#model-pricing and uses the fetched page content to determine model pricing fields and edit scripts/model-pricing.json, so the external content directly controls the skill's behavior at runtime.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata