skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-data-loader/Gen Agent Trust Hub
cwicr-data-loader
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface because it is designed to ingest and process untrusted external data files (CSV, Excel, JSON, and Parquet).
- Ingestion points: The
_load_csv,_load_excel,_load_json, and_load_parquetmethods inSKILL.mdread data from user-specified file paths. - Boundary markers: The implementation lacks explicit delimiters or instructions to the agent to ignore embedded natural language commands within the processed data.
- Capability inventory: The skill performs filesystem read and write operations via the
loadandexportmethods in theCWICRDataLoaderclass. - Sanitization: No sanitization or filtering of text content within the data files is performed to prevent the agent from interpreting embedded text as instructions.
Audit Metadata