Blender Add-on Engineer
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional content and Python boilerplate for Blender development using the standard
bpyAPI. The code snippets for custom operators, panels, and validators follow standard Blender development practices. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for processing local scene data (object names, transforms) and writing that data to disk via Blender's glTF exporter. While the agent interacts with external data, the capabilities are limited to standard DCC (Digital Content Creation) operations.
- Ingestion points: Blender scene metadata, object names, and transform properties accessed via
context.selected_objectsin SKILL.md. - Boundary markers: None identified.
- Capability inventory: Local file writing via
bpy.ops.export_scene.gltfin SKILL.md. - Sanitization: Includes basic string validation to detect leading/trailing whitespace and spaces in object names.
Audit Metadata