csv-data-wrangler
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides purely instructional content for data processing tasks using established libraries and command-line tools such as pandas, polars, and DuckDB. No malicious patterns, obfuscation, or unauthorized access attempts were identified.- [INDIRECT_PROMPT_INJECTION]: The skill defines workflows for ingesting and processing external CSV data, which creates a potential surface for indirect prompt injection. 1. Ingestion points: CSV file loading and profiling (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: The skill is purely instructional and does not include scripts with subprocess or file-write capabilities. 4. Sanitization: Not specified beyond data type validation. Given the lack of dangerous instructions or script-based capabilities, the risk remains minimal.
Audit Metadata