skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/validation-rules-builder/Gen Agent Trust Hub
validation-rules-builder
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implementation consists of a transparent Python library for data validation. No unauthorized network operations, credential access, or malicious code patterns were found.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external construction data, which presents an ingestion surface.
- Ingestion points: Project data provided by the user in CSV, Excel, or JSON format as described in
instructions.md. - Boundary markers: None explicitly defined in the instructions to separate data from instructions.
- Capability inventory: Filesystem access requested in
claw.jsonfor reading/writing data and execution of validation logic. - Sanitization: The skill uses predefined RegEx patterns, numeric range checks, and enum validation to ensure data integrity.
Audit Metadata