The Agent Skills Directory

[PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters or override system prompts. Directives to prioritize reference files over generic approaches are standard grounding instructions for expert-persona skills.
[DATA_EXFILTRATION]: No hardcoded credentials, sensitive file paths, or unauthorized network exfiltration patterns were identified in the skill body or reference files.
[OBFUSCATION]: The content is clear and readable. No Base64 encoding, zero-width characters, or homoglyph attacks were detected.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute code from external sources. Code snippets provided for Maya (MEL/Python), Blender (Python), and Unity (C#) are static examples intended for the agent to share with the user as best practices.
[INDIRECT_PROMPT_INJECTION]: The skill processes character rigging data and animation files (e.g., FBX). This is a low-risk attack surface, and the skill does not contain any mechanisms that would allow untrusted data to execute commands or manipulate the agent's core instructions.

rigging-animation