guided-doc-writing
Warn
Audited by Snyk on Jul 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill requires running compose-agentsmd which fetches external rules from github:metyatech/agent-rules (see github:metyatech/agent-rules@HEAD/rules/domains/skill/repository.md) and those fetched rules directly control agent instructions, so this external repository is a runtime dependency that can change agent prompts.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata