The Agent Skills Directory

[SAFE]: The skill provides legitimate instructional content and architectural patterns for Unity UI development. No malicious patterns, such as credential harvesting, unauthorized network communication, or obfuscation, were detected. The author context and referenced resources are consistent with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an inherent vulnerability surface for indirect prompt injection, which is typical for code-editing assistants that ingest and modify project files. This surface is considered safe given the skill's intended use case and proactive constraints on external data loading.
Ingestion points: The skill reads existing UXML, USS, and asset files from the local Unity project environment to provide context for modifications (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the files it processes.
Capability inventory: The skill has the authority to write and modify UXML layouts, USS stylesheets, and C# scripts within the local workspace (SKILL.md, references/custom-elements.md, references/ui-runtime-binding.md).
Sanitization: There are no explicit instructions for sanitizing or escaping content retrieved from project files before it is re-interpolated into generated code.

ui-uitk