The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and modify local RPG Maker game files, which represents a potential attack surface if project files contain malicious content.
Ingestion points: The skill instructions and scripts (e.g., audit_rpg_db.py) read from data/*.json and js/plugins.js within a project directory.
Boundary markers: The skill relies on standard Markdown formatting to separate instructions from code; no specific guardrails or delimiters are provided for the data being processed.
Capability inventory: The skill performs local file read/write operations and documents shell commands for running the game engine (nw.exe) and validating data (node, jq).
Sanitization: The provided Python and JavaScript examples process JSON data directly without explicit escaping or filtering of potentially malicious strings embedded in game data.
[COMMAND_EXECUTION]: The skill provides legitimate example commands for game development workflows.
Evidence: Documentation includes commands for launching the RPG Maker MZ test environment (nw.exe), using jq to query JSON data, and using Node.js to validate project files.
Context: All commands are standard tools for the engine's ecosystem and are intended for local development use.

rpg-maker