omni-model-explorer

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

• Potentially malicious external URL detected (high risk: 0.90). The skill performs runtime requests to the Omni API (e.g., https://yourorg.omniapp.co/api/v1/models and https://yourorg.omniapp.co/api/v1/models/{modelId}/yaml) and those responses include an "ai_context" field that can directly supply instructions for the agent, so the external content can control prompts and is a required runtime dependency.