The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The README.md recommends installing the companion tool polars-mcp from a personal GitHub repository (github.com/r-brink/polars-mcp) using uvx. This encourages the agent to advise the user to download and execute code from a third-party source not associated with the official Polars organization.
[EXTERNAL_DOWNLOADS]: The skill points to official Polars documentation at docs.pola.rs and the polars-inc GitHub organization. These are vendor-owned resources and are standard for library documentation lookup.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external data files, which presents a surface for indirect prompt injection.
Ingestion points: Data scanning functions such as pl.scan_csv, pl.scan_parquet, and pl.scan_ndjson in SKILL.md and references/lazy-api.md.
Boundary markers: No instructions are provided for using delimiters or boundary markers to isolate data content from the prompt context.
Capability inventory: The skill allows the agent to perform a wide range of data transformations, aggregations, and joining operations using the Polars API.
Sanitization: There are no specific sanitization or filtering steps recommended for data content beyond basic type casting.

polars