blender-modeler
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for 3D modeling in Blender using the Model Context Protocol (MCP). No malicious patterns, such as prompt injection, unauthorized data access, or obfuscation, were detected. The instructions follow industry standards for 3D asset creation and scene management.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing user-provided reference images and concept art. While no malicious intent is detected, this represents an attack surface for indirect prompt injection where malicious instructions could be embedded in the input data.
- Ingestion points: Reference images or concept photos attached by users (documented in references/asset-pipeline.md).
- Boundary markers: None present.
- Capability inventory: Extensive use of execute_blender_code via MCP to run Python scripts within the Blender environment and file-writing operations via bpy.ops.wm.save_mainfile (documented in references/mcp-integration.md).
- Sanitization: None present.
Audit Metadata