blender-to-unity

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses mcp__blender__execute_blender_code to run Python scripts within Blender for exporting models and execute_code to run C# scripts in Unity for post-import adjustments. This is the primary mechanism for the skill's automation.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it retrieves data from the Blender environment (such as object names and material properties) and uses them to construct C# scripts executed in the Unity editor.
  • Ingestion points: Object and material names are retrieved from Blender via mcp__blender__get_scene_info and specialized Python scripts.
  • Boundary markers: No specific boundary markers are used to isolate untrusted data when generating scripts.
  • Capability inventory: The skill utilizes tool execution capabilities (execute_blender_code, execute_code) and file system access provided by the platform.
  • Sanitization: The instructions do not specify sanitization or escaping for Blender-sourced strings before they are interpolated into C# command templates like GameObject.Find(\"<asset name>\").
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 05:32 AM
Security Audit — agent-trust-hub — blender-to-unity