skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/few-shot-examples/Gen Agent Trust Hub
few-shot-examples
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to provide static data and formatting logic for prompt engineering. No suspicious code patterns were found.
- [SAFE]: No external network requests or remote code downloads are performed. All URLs in the documentation point to official homepages or educational resources.
- [SAFE]: The skill does not handle sensitive information, hardcoded credentials, or unauthorized file system operations.
- [PROMPT_INJECTION]: The skill is designed to process user-provided construction data (CSV, JSON, Excel). While this represents an ingestion surface for indirect prompt injection, the risk is mitigated by the absence of dangerous capabilities (e.g., shell access, network requests) in the skill's code. There is no evidence of adversarial instructions within the provided files.
Audit Metadata