unity-procedural-gen
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a translation layer for user-provided 'DESIGN INTENT', which creates a potential surface for indirect prompt injection where malicious instructions could be embedded in the design specifications to influence generated code.
- Ingestion points: The skill specifically processes user-provided 'DESIGN INTENT' blocks to generate C# code, assets, and compute shaders as defined in the
globssection ofSKILL.md. - Boundary markers: There are no explicit boundary markers or instructions defined in the skill to treat the 'DESIGN INTENT' as untrusted data or to ignore embedded instructions within that data.
- Capability inventory: The skill allows the agent to generate and modify
.cs(C# scripts),.asset(Unity assets), and.compute(Compute shaders) files. - Sanitization: The skill lacks explicit sanitization or validation logic to filter potentially malicious instructions within the design intents before they are used to generate code.
Audit Metadata