The Agent Skills Directory

[PROMPT_INJECTION]: The skill facilitates the ingestion and processing of data from untrusted external sources, creating a surface for indirect prompt injection attacks.
Ingestion points: The skill provides instructions for reading data via pl.read_csv, pl.scan_csv, pl.read_parquet, pl.read_json, pl.read_ndjson, pl.read_excel, pl.read_database, and pl.read_database_uri (found in SKILL.md and references/io_guide.md).
Boundary markers: The instructions do not define boundary markers or 'ignore embedded instructions' warnings for the data being processed.
Capability inventory: The skill includes capabilities to write data back to the file system or databases using write_csv, write_parquet, write_ndjson, write_json, write_excel, write_ipc, sink_parquet, and write_database (found in references/io_guide.md).
Sanitization: There are no descriptions of content sanitization, validation, or escaping for the data loaded into the agent's context.

polars