create-agentsmd-instructions

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

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly instructs the agent at runtime to "Review all following documentations" and lists external docs that will directly influence how the AGENTS.md is composed, namely https://docs.github.com/en/copilot/customizing-copilot/adding-repository-custom-instructions-for-github-copilot and https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models, so these URLs are runtime dependencies that control the agent's instructions.