mlflow-genai-foundation

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

• Potentially malicious external URL detected (high risk: 0.70). The skill includes runtime calls to load prompts from the MLflow Prompt Registry (e.g., mlflow.genai.load_prompt("prompts:/my_app_assistant_prompt/production") and "prompts:/cost_analyst_prompt/production"), which fetch external prompt content that directly controls agent instructions.