wazza-3d
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for using the Blender CLI to import and export 3D models (GLB to FBX conversion), which is a standard workflow for asset preparation.
- [DYNAMIC_EXECUTION]: The skill utilizes the --python-expr flag in Blender to automate asset imports and exports through Python snippets. These operations are limited to static file handling templates.
- [INDIRECT_PROMPT_INJECTION]: The skill processes text returned from API responses. It mitigates injection risks by instructing the agent to treat all run result text as data and never as instructions, establishing a clear processing boundary.
- [SAFE]: The skill interacts with authorized vendor domains (api-pro.wazza.ai) and follows proper secret management protocols by directing the agent to avoid exposing API keys in conversation or files.
Audit Metadata