create-3d-scene
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides legitimate Python code for Blender automation. It follows standard practices for scene setup, including data cleanup and organizational hierarchy.
- [COMMAND_EXECUTION]: The skill documentation describes executing Python scripts via the Blender CLI (blender --background --python setup_scene.py). This is a standard and expected operation for the primary purpose of the skill.
- [DATA_EXFILTRATION]: No unauthorized network activity or sensitive file access was identified. The skill writes render output to /tmp/, which is a standard location for temporary files.
- [PROMPT_INJECTION]: While the skill ingests external inputs like asset paths and scene specifications, it lacks patterns typical of indirect injection exploitation. The provided examples show these inputs being used as parameters for API calls rather than being unsafely evaluated.
Audit Metadata