The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions to override agent behavior, bypass safety filters, or reveal system prompts were detected.
[Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or unauthorized network operations were found. The skill focuses entirely on shader code generation.
[Remote Code Execution & Dependencies] (SAFE): The skill does not include any commands to download or execute external scripts, nor does it define any third-party software dependencies.
[Obfuscation] (SAFE): All content is written in clear, human-readable markdown and YAML. No encoded or hidden characters were detected.
[Indirect Prompt Injection] (LOW): The skill ingests user requirements to generate shaders and C# code. While it lacks explicit boundary markers for untrusted user input, it follows a structured workflow for code generation which is its primary purpose.
[Privilege Escalation] (SAFE): No commands involving elevated permissions, such as sudo or administrative overrides, are present.

unity-shader