The Agent Skills Directory

[SAFE]: The skill contains no executable code or scripts; it is strictly a markdown-based instructional framework for task routing.
[SAFE]: No network operations, external downloads, or remote code execution patterns were detected.
[SAFE]: The skill references local paths for other shader skills (e.g., /mnt/skills/user/shader-fundamentals/SKILL.md), which is standard behavior for modular AI agent skill sets.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests user requirements to perform routing, it lacks any high-privilege capabilities (like file writing or network access) that could be exploited through malicious input in this context. The risk is negligible.

shader-router