create-command

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires fetching the latest official documentation at runtime (https://code.claude.com/docs/en/skills), and that fetched content is used to guide/drive the skill-generation prompts and behavior, so it is a runtime external dependency that can directly control agent instructions.