skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/co2-carbon-footprint/Gen Agent Trust Hub
co2-carbon-footprint
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill utilizes standard Python data science libraries to perform its calculations.\n
- Evidence: Employs
pandasfor data structuring andopenpyxlfor generating Excel reports. These are well-known packages from trusted registries.\n- [SAFE]: The implementation follows construction industry standards for CO2 estimation without malicious behavior.\n - Evidence: The Python code in
SKILL.mddefines legitimate classes for life cycle stages and material categories based on EN 15978.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes BIM model data from external files, establishing a standard ingestion surface.\n - Ingestion points: The
calculate_from_dataframemethod reads data from files provided by the user (e.g.,bim_quantities.xlsx).\n - Boundary markers: While no explicit data delimiters are used in the code, the
instructions.mdfile mandates input validation before processing.\n - Capability inventory: The skill utilizes filesystem permissions to read quantities and write Excel reports.\n
- Sanitization: Input data is cast to float types during calculation, which provides basic structural validation.
Audit Metadata