skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-location-factor/Gen Agent Trust Hub
cwicr-location-factor
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate business logic for construction cost estimation, adjusting base costs for labor, materials, and equipment across various global locations relative to established national averages.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external project data and cost items to perform calculations, which represents an ingestion surface for potentially untrusted data.
- Ingestion points: Project data enters the skill through external files (Parquet, Excel, JSON) or structured list/dictionary inputs processed by the
adjust_estimateandadjust_costmethods inSKILL.md. - Boundary markers: No explicit boundary markers or instruction-ignoring directives are implemented in the code to distinguish between data and potential embedded instructions.
- Capability inventory: The skill has the capability to write results to the local file system using the
pandas.ExcelWriterclass in theexport_factorsmethod. - Sanitization: No sanitization or schema validation is explicitly performed on input data beyond standard pandas processing.
Audit Metadata