data-governance-lineage

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill includes a Python script that processes external data from a CSV file (input.csv). While this creates a potential surface for indirect prompt injection if the data contains malicious instructions, the script's capabilities are limited to performing mathematical summaries (means, standard deviations, and quantiles) and outputting the results to a JSON file.
  • Ingestion points: External data is ingested via pd.read_csv() in scripts/data_governance_lineage_diagnostics.py.
  • Boundary markers: The instructions do not define explicit delimiters for the ingested CSV content.
  • Capability inventory: The script performs data transformation and statistical analysis using pandas, with no command execution, dynamic code evaluation, or network operations.
  • Sanitization: The script uses pd.to_numeric(errors='coerce') and pd.to_datetime(errors='coerce'), which effectively neutralizes non-numeric or non-date content before calculation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 02:04 PM