querying-mlflow-metrics
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The script
scripts/fetch_metrics.pymakes network requests to an MLflow tracking server usingurllib.request. The target server URL is provided by the user via arguments, and the activity is consistent with the skill's purpose of fetching trace metrics. No unauthorized exfiltration of sensitive local data was observed.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API (MLflow server) into the agent context.\n - Ingestion points: Data is fetched from the MLflow tracking server in
scripts/fetch_metrics.py.\n - Boundary markers: None identified.\n
- Capability inventory: No subprocess calls, dynamic execution (eval/exec), file system write operations, or unauthorized network operations are present.\n
- Sanitization: Content is parsed as JSON with no additional filtering or validation of the metric values.
Audit Metadata