polars
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of documentation and reference material for the Polars data manipulation library. No malicious scripts or instructions were found within the markdown files or referenced guides.
- [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install the 'polars' library using standard package managers like uv. Polars is a well-known, legitimate open-source technology for data processing.
- [PROMPT_INJECTION]: As a tool for data manipulation, the skill describes processes for reading data from external sources, which is a known surface for indirect prompt injection. Ingestion points: Methods like 'pl.read_csv', 'pl.read_parquet', and 'pl.read_database' documented in 'references/io_guide.md' allow loading external data. Boundary markers: Not mentioned in the documentation. Capability inventory: The skill documents extensive data manipulation and output capabilities, including writing to local and cloud storage. Sanitization: No specific guidance on sanitizing data for use in LLM contexts is provided.
Audit Metadata