Skills
skills/terrylica/cc-skills/mlflow-python/Gen Agent Trust Hub

mlflow-python

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external data which constitutes an indirect prompt injection surface.
  • Ingestion points: The scripts/log_backtest.py script reads user-provided CSV files, and scripts/query_experiments.py and scripts/get_metric_history.py ingest data from remote MLflow server responses.
  • Boundary markers: No explicit boundary markers or instructions to ignore potential instructions within the data are used when presenting findings to the agent.
  • Capability inventory: The skill can read local files, perform network operations to MLflow servers, and execute Python scripts to log metrics and parameters.
  • Sanitization: The ingested data is parsed into structured formats (DataFrames) but the content is not sanitized for natural language instructions before being displayed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 03:38 AM