The Agent Skills Directory

[SAFE]: No security issues detected. The skill's behavior is consistent with its stated purpose of agent evaluation using official MLflow and Databricks tools.\n- [COMMAND_EXECUTION]: Utilizes subprocess.run to execute local MLflow CLI commands and Python utilities for environment introspection and automation, which is standard for local development tools.\n- [EXTERNAL_DOWNLOADS]: Accesses documentation and guidelines from mlflow.org, which is a well-known and trusted technology provider.\n- [REMOTE_CODE_EXECUTION]: Generates and executes local Python scripts from templates to facilitate evaluation workflows. This behavior is restricted to the local environment and handles user-provided data for the purpose of automation.

agent-evaluation