The Agent Skills Directory

[SAFE]: The skill operates as a local developer tool for game modding. It handles user-provided game data and generates source code for modding purposes without any suspicious or hidden behaviors.
[COMMAND_EXECUTION]: The skill includes Python scripts (pnach.py, override.py) that perform file parsing and code generation. These scripts use standard Python libraries and do not execute arbitrary shell commands or malicious subprocesses.
[DATA_EXPOSURE_AND_EXFILTRATION]: No network operations were detected in the skill's scripts or instructions. It does not access sensitive system paths (like SSH keys or cloud credentials) and only interacts with game-related files within the workspace.
[DYNAMIC_EXECUTION]: The script pnach.py uses importlib.util to load its own helper script override.py. This is a standard programming pattern for modularity and is safe here as it only loads local files distributed as part of the skill.
[INDIRECT_PROMPT_INJECTION]: While the skill processes external data (patch files and Ghidra maps), it uses a strict parser that extracts specific data fields. It does not interpolate untrusted raw text into agent instructions in an unsafe manner.

console-mod