csv-data-wrangler
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or unauthorized access patterns were detected. The skill acts as a set of instructions for using standard tools like pandas and DuckDB.
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted CSV files, creating a surface for indirect prompt injection.
- Ingestion points: CSV files processed according to workflows in SKILL.md.
- Boundary markers: Absent; no explicit delimiters are suggested for processed content.
- Capability inventory: Command execution via CLI tools (csvkit, xsv) and data processing with Python libraries (pandas, polars, duckdb).
- Sanitization: Not specified for the purpose of instruction isolation.
Audit Metadata