crossborder-listing-localization

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

• Potentially malicious external URL detected (high risk: 0.90). The runner performs runtime HTTP requests to the external endpoint https://ai-skills.ai/api/execute (DEFAULT_BASE_URL) and the skill relies on that endpoint to obtain model execution/results that directly control agent prompts, so this is a required runtime dependency that controls the agent.