unity-qframework

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Unity environment such as GameObject names, hierarchy paths, and project configuration files, which are used as inputs for code generation and settings management. \n
  • Ingestion points: GameObject names, hierarchy paths, and configuration files (e.g., ProjectConfig.json).\n
  • Capability inventory: File writing (code generation), directory deletion (AssetBundle clearing), and assembly scanning.\n
  • Boundary markers: Absent.\n
  • Sanitization: Not explicitly specified for input parameters used in generation tasks.\n- [DYNAMIC_EXECUTION]: The skill generates C# source code and Designer files directly to the project directory. This code is subsequently compiled and executed by the Unity Editor. These operations are restricted to specific execution modes due to their impact on the project state.\n- [COMMAND_EXECUTION]: The skill includes functionality to delete the AssetBundles and StreamingAssets directories at the filesystem level. This is a destructive and permanent operation intended for clearing build artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 06:52 PM
Security Audit — agent-trust-hub — unity-qframework