claude-api
Warn
Audited by Snyk on Jun 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent to "WebFetch" live SDK/docs listed in shared/live-sources.md at runtime (e.g., the repo referenced in the manifest https://github.com/anthropics/skills), meaning external repository/documentation content would be fetched during runtime and used to determine exact API calls and generated code/instructions.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata