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 (e.g., https://code.claude.com/docs/en/skills), and that fetched content is used to drive the generated SKILL.md and agent prompts, so it directly influences agent instructions.