The Agent Skills Directory

[SAFE]: The skill provides documentation for the Polars library and does not contain any executable scripts, shell commands, or obfuscated content.
[INDIRECT_PROMPT_INJECTION]: The skill describes tools for ingesting external data from various file formats and databases, which represents a potential surface for indirect prompt injection if the agent processes untrusted data.
Ingestion points: pl.read_csv, pl.scan_parquet, pl.read_database, and various cloud storage connectors documented in references/io_guide.md.
Boundary markers: None present in the documentation examples.
Capability inventory: None. The skill consists entirely of markdown files and does not contain tools with execution capabilities.
Sanitization: Not applicable to this documentation-only skill.

polars