skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/energy-simulation/Gen Agent Trust Hub
energy-simulation
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
- Ingestion points: Untrusted data enters the agent context via CSV, Excel, and JSON files provided by the user as referenced in instructions.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore embedded commands within the ingested data.
- Capability inventory: The skill requests filesystem permission in claw.json and performs data processing using the classes in SKILL.md.
- Sanitization: The provided code and instructions lack explicit sanitization or filtering of the content within the processed files before it is presented to the agent.
Audit Metadata