The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from a versioned CSV file (defaulting to ./compliance/data-safety.csv). This creates a surface for indirect prompt injection where malicious instructions could be embedded in the CSV data. However, the skill performs structural validation and the data is intended for a specific API schema, which mitigates the risk.
[COMMAND_EXECUTION]: The skill invokes a CLI tool (gplay) to perform compliance tasks. It requires an explicit --confirm flag for live write operations, which acts as a safety barrier against accidental execution.

gplay-compliance