skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-quality-check/Gen Agent Trust Hub
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