teaching-style-patterns

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 reads agent-ruleset.json that references the external rules source "github:metyatech/agent-rules@HEAD" (https://github.com/metyatech/agent-rules), so at runtime the skill will fetch remote GitHub-hosted rule content that directly controls agent instructions.