godot-ui-designer
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interprets natural language descriptions to generate UI code and scenes. This creates a potential surface for instructions embedded in data to influence the agent's code generation.
- Ingestion points: Natural language UI descriptions processed by the agent.
- Boundary markers: None provided to distinguish user requirements from generated content.
- Capability inventory: Tools for file creation (
save_scene) and scene testing (play_scene) allow the agent to write and execute scripts. - Sanitization: No explicit sanitization or validation of input data is defined in the skill instructions.
- [DYNAMIC_EXECUTION]: The skill generates GDScript components and utilizes the
play_scenetool to execute them locally for testing and design verification. This is standard behavior for a development-focused AI assistant.
Audit Metadata