agent-evaluation-mlflow
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains strings like 'Ignore previous instructions' used exclusively within example evaluation datasets and detection logic (PromptInjectionScorer) to test agent robustness.
- [EXTERNAL_DOWNLOADS]: The skill references the installation of 'mlflow', which is a well-known and trusted package for machine learning lifecycle management.
- [DATA_EXFILTRATION]: The skill configures an internal MLflow tracking server for telemetry. It specifically includes guidelines and scorers designed to detect and prevent the exposure of PII and sensitive credentials.
Audit Metadata