The Agent Skills Directory

[SAFE] (SAFE): The skill is primarily composed of instructional documentation and regex-based validation rules for game engine code. It does not perform any system operations, network calls, or file modifications.
[Indirect Prompt Injection] (LOW): The skill ingests untrusted data in the form of game source code (*.cs, *.gd, *.ts) for analysis. While this is a theoretical attack surface, the skill lacks any high-risk capabilities (such as shell execution or file writing) that could be exploited by malicious code comments or patterns. The analysis is limited to providing feedback based on predefined regex identifiers.
[Metadata Poisoning] (SAFE): The metadata fields (name, description) are descriptive and aligned with the skill's stated purpose, with no deceptive instructions or hidden payloads detected.

llm-game-development