searching-mlflow-docs

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches runtime content from https://mlflow.org/docs/latest/llms.txt and then loads .md files from https://mlflow.org/docs/latest/[path].md to inject verbatim documentation/code blocks into the agent's output, meaning external content from those URLs directly controls the agent's responses.