csv-data-wrangler
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of documentation and workflow guidance for data processing. It recommends standard, well-known libraries and tools including pandas, polars, DuckDB, and csvkit for handling tabular data.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external CSV files, which is an inherent attack surface for indirect prompt injection. However, the documentation emphasizes best practices such as proper parsing, encoding detection, and data validation, which are standard security and integrity measures for data processing.
Audit Metadata