skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-resource-analyzer/Gen Agent Trust Hub
cwicr-resource-analyzer
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implementation uses standard data analysis libraries for construction planning and does not contain any malicious patterns or unauthorized operations.
- [PROMPT_INJECTION]: The skill processes external data (CSV, Excel, JSON), which represents a theoretical surface for indirect prompt injection. However, this is assessed as safe given the lack of high-risk capabilities like network access or dynamic code execution. 1. Ingestion points: Data input formats (CSV, Excel, JSON) described in instructions.md. 2. Boundary markers: No explicit delimiter instructions. 3. Capability inventory: Filesystem access for data reading. 4. Sanitization: No specific input sanitization for instructions within data files.
Audit Metadata