skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/co2-estimation/Gen Agent Trust Hub
co2-estimation
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external BIM exports and Excel files, which represents an attack surface for indirect prompt injection.
- Ingestion points: The skill uses
pd.read_excel()to ingest project data inSKILL.md(e.g.,bim_elements.xlsx,bim_export.xlsx). - Boundary markers: There are no explicit delimiters or instructions to the AI to ignore embedded instructions within the processed data files.
- Capability inventory: The skill possesses filesystem capabilities for reading input data and writing reports using the
openpyxlengine. - Sanitization: No input sanitization or content validation is performed on the data before it is processed by the logic or presented to the user.
Audit Metadata