data-quality-checker

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through the processing of untrusted input files.
  • Ingestion points: Content is read from the file path provided to the --file argument in scripts/check_data_quality.py.
  • Boundary markers: The script does not utilize delimiters or explicit instructions to the agent to disregard instructions embedded in the analyzed documents.
  • Capability inventory: The skill can read local files and write results to the reports/ directory. The test suite (scripts/tests/test_check_data_quality.py) also utilizes subprocess.run to execute the main script for validation purposes.
  • Sanitization: There is no escaping or sanitization of document content before it is parsed by regular expressions or included in the context fields of the generated reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 12:05 AM