skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/resource-allocation-optimizer/Gen Agent Trust Hub
resource-allocation-optimizer
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 ingest and process project data from external formats including CSV, Excel, and JSON, which creates a potential surface for indirect prompt injection.
- Ingestion points: Project scheduling data and resource parameters provided via file paths or direct user input as described in instructions.md.
- Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions to prevent the agent from following commands embedded within user data.
- Capability inventory: The skill manifest requests filesystem permissions to facilitate data export functions.
- Sanitization: The instructions include a requirement to validate inputs before processing, but specific sanitization or filtering logic for embedded instructions is not defined.
Audit Metadata