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 external documentation at runtime (https://mlflow.org/docs/latest/llms.txt and https://mlflow.org/docs/latest/[path].md) and injects the fetched .md content/code blocks verbatim into the agent context, which meets the criteria for remote content directly controlling agent outputs.