The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute mlflow traces CLI commands to search and retrieve trace information from the local environment.
[EXTERNAL_DOWNLOADS]: Fetches additional documentation and filter syntax from the official MLflow website (mlflow.org).
[INDIRECT_PROMPT_INJECTION]: The skill retrieves MLflow traces, which are external data sources that could potentially contain instructions. 1. Ingestion points: mlflow traces search and mlflow traces get outputs. 2. Boundary markers: The instructions do not define delimiters to isolate the retrieved data from instructions. 3. Capability inventory: Execution of mlflow CLI commands. 4. Sanitization: No explicit content validation or sanitization is described.

retrieving-mlflow-traces