The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (SAFE): The script performs network requests to a user-provided MLflow server URL using the standard urllib library. This is the intended purpose of the skill and does not involve downloading or executing external code.\n- [DATA_EXFILTRATION] (SAFE): No access to sensitive local file paths (e.g., SSH keys, cloud credentials) or hardcoded secrets was detected.\n- [COMMAND_EXECUTION] (SAFE): The script does not utilize functions for shell command execution or dynamic code evaluation such as os.system, subprocess.run, or eval.\n- [PROMPT_INJECTION] (SAFE): No instructions designed to override agent behavior or bypass safety filters were found in the documentation or metadata.\n- [DATA_EXPOSURE] (SAFE): The data ingested from the MLflow API is formatted and printed to the console; the skill lacks capabilities to execute or write this data back to the filesystem, minimizing the risk from potentially malicious external data.

querying-mlflow-metrics