skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/lifecycle-carbon-calculator/Gen Agent Trust Hub
lifecycle-carbon-calculator
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, which introduces a potential surface for indirect prompt injection if the data contains malicious instructions.\n
- Ingestion Points: The
instructions.mdfile specifies that the agent should gather project data from user-provided file paths or direct inputs in formats such as CSV, Excel, and JSON.\n - Boundary Markers: The skill lacks explicit boundary markers or delimiters (such as XML tags or unique identifiers) to help the agent distinguish between data and potential instructions embedded within the files.\n
- Capability Inventory: The skill is granted
filesystempermissions viaclaw.jsonto handle project data.\n - Sanitization: Although
instructions.mdincludes a directive to "Validate inputs before processing," there is no specific implementation of sanitization or escaping logic in the provided Python code to handle adversarial content within data files.
Audit Metadata