unity-material

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection where malicious instructions could be embedded in the data processed by the agent.
  • Ingestion points: Material names (name), asset paths (path, savePath, materialPath, texturePath, sourcePath), and structured JSON data in batch operations (material_create_batch, material_assign_batch, material_set_colors_batch, material_set_emission_batch).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the input data are present in the documentation.
  • Capability inventory: The skill allows creating material assets on the file system, modifying existing material properties (colors, textures, floats, shaders), and assigning materials to game objects.
  • Sanitization: There is no mention of input sanitization or validation for the provided strings and paths before they are used in Unity operations.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 08:10 AM