blender-shader-nodes
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill generates Python code based on internal templates to programmatically build shader node trees. This code is intended for execution within the Blender environment via the
execute_blender_codetool. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided descriptions of materials and textures to generate these scripts. This creates a surface where untrusted input influences generated code, though the risk is mitigated by the highly structured nature of the provided API references.
- Ingestion points: User requests for specific material designs (SKILL.md).
- Boundary markers: Not present.
- Capability inventory: Live Python script execution through
execute_blender_code(SKILL.md). - Sanitization: The skill relies on the agent adhering to the static
ShaderNodetype strings and linking patterns defined inreferences/python_api.md.
Audit Metadata