dataset-quality-audit

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill operates locally to provide data quality metrics as described. It does not perform network operations, credential access, or shell command execution.- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted data files. Ingestion points: scripts/data_quality_checker.py reads external CSV, Excel, and JSON files provided via command-line arguments. Boundary markers: The generated report includes data values and column names without encapsulation or instruction-ignore markers. Capability inventory: The script's capabilities are limited to reading input files and writing JSON reports to the local file system. Sanitization: The tool does not sanitize or escape data content before including it in the output report.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:12 AM