dataset-health-audit
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate data auditing functionality. It uses standard Python libraries to analyze local files and does not engage in unauthorized network communication or command execution.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data files in scripts/data_quality_checker.py. Ingestion points: Local CSV, Excel, TSV, and JSON files are loaded in the load_data function. Boundary markers: Results are returned as structured JSON. Capability inventory: Script is limited to local file system reads and writing the audit report to a user-specified path. Sanitization: Values from the dataset are included in generated suggestions without specific escaping.
Audit Metadata