railway-docs

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

• Potentially malicious external URL detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to "Fetch up-to-date Railway documentation" and lists runtime-fetchable LLM-optimized sources (e.g., https://docs.railway.com/api/llms-docs.md) which would be fetched and injected into the agent's prompt/context, so these external URLs directly control agent instructions at runtime.