skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/quality-control-workflow/Gen Agent Trust Hub
quality-control-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external project data in formats like CSV, Excel, and JSON, which serves as an ingestion point for potentially untrusted data. While the instructions mandate input validation, the lack of explicit boundary markers or sanitization logic in the core code creates a theoretical surface for indirect prompt injection. This risk is considered inherent to the skill's data-processing functionality.
Audit Metadata