data-quality-check

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface detected through the ingestion of external construction data.
  • Ingestion points: The skill reads project data from Excel, CSV, and JSON files as described in instructions.md and the examples in SKILL.md.
  • Boundary markers: No specific delimiters or markers are used to separate user-provided data from system instructions in the prompt logic.
  • Capability inventory: The skill performs filesystem write operations using pandas.ExcelWriter for report generation.
  • Sanitization: The checker implementation provides regex-based validation for identifiers and specific construction metrics, which serves as a localized sanitization mechanism.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:28 AM