The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified in the skill's instructions or scripts.
[DATA_PROCESSING]: The skill ingests untrusted data from CSV and JSON files, which is its primary purpose. While this introduces a surface for indirect prompt injection, it is considered standard for this category of utility.
Ingestion points: scripts/csv_read.py and scripts/csv_write.py ingest local file data.
Boundary markers: Data is processed and displayed without specific boundary delimiters, which is typical for CLI-based data tools.
Capability inventory: The skill can read and write files on the local filesystem.
Sanitization: Standard Python CSV parsing is used, which does not interpret data as code or instructions.

csv-handler