skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/site-logistics-optimization/Gen Agent Trust Hub
site-logistics-optimization
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it is designed to ingest and process potentially untrusted project data from external sources.
- Ingestion points: Ingests project data, file paths, and parameters in CSV, Excel, and JSON formats as described in
instructions.md. - Boundary markers: The instructions lack explicit boundary markers or delimiters to differentiate between data content and potential instructions during processing.
- Capability inventory: The skill manifest (
claw.json) requestsfilesystempermissions, andinstructions.mdspecifies the capability to export data to Excel, CSV, and JSON files. - Sanitization: While
instructions.mdrequires input validation, there are no specific details regarding the sanitization or filtering of external content to prevent embedded instruction execution.
Audit Metadata