skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/resource-pool-optimizer/Gen Agent Trust Hub
resource-pool-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project data from external files, which creates a vulnerability to indirect prompt injection if the data contains malicious instructions.
- Ingestion points: Untrusted CSV, Excel, and JSON files provided by the user in
instructions.md. - Boundary markers: Absent; the instructions do not specify delimiters to segregate data from instructions.
- Capability inventory: The skill requests
filesystemaccess viaclaw.json, allowing the agent to read sensitive data or write malicious files if subverted. - Sanitization: No sanitization or validation logic for the content of ingested files is defined.
Audit Metadata