materials
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill instructions and Python scripts reveals no malicious patterns, unauthorized network activity, or credential exposure. The skill operates within the expected boundaries of Unreal Engine editor automation.
- [COMMAND_EXECUTION]: The skill correctly implements editor automation through the unreal Python API and standard toolsets. Scripts like create_material.pyx and create_instance.pyx are designed for legitimate asset management tasks.
- [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection by processing external material graph data (HLSL code, node metadata) via export_material_graph. However, the risk is mitigated by the domain-specific nature of the task and the recommended use of compilation diagnostics.
- Ingestion points: MaterialNodeService.export_material_graph and get_function_info in reference.md.
- Boundary markers: Not explicitly specified for prompt interpolation of graph data.
- Capability inventory: Asset creation, modification, and Python script execution via the unreal module.
- Sanitization: Automated shader compilation and diagnostic checks (get_material_diagnostics) are utilized to validate material integrity.
Audit Metadata