blender-uv-texturing
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates and executes Python code using the
mcp__blender__execute_blender_codetool. This is a primary feature of the skill, allowing it to manipulate Blender's internal data structures (UV layers, materials, nodes) and perform complex operations like texture baking.- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for potentially untrusted data from external sources. - Ingestion points: External image files are loaded via their file paths (
bpy.data.images.load) and mesh data is processed for UV projection. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions within processed asset names or metadata.
- Capability inventory: The skill uses Python execution within Blender, file reading (
Read), and file writing (saving baked textures to/tmp/). - Sanitization: There is no explicit sanitization of object names or file paths within the provided Python recipes.
Audit Metadata