blender-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to use the Blender executable via the command line to process scenes and run scripts, using patterns such as
blender scene.blend --background --python scripts/change_scene.py. - [DYNAMIC_EXECUTION]: The workflow relies on the agent generating Python scripts at runtime to perform substantial edits or transformations within the Blender environment.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes user-provided task descriptions to generate and execute code.
- Ingestion points: User instructions for 3D modeling, rigging, or animation tasks (SKILL.md).
- Boundary markers: None specified for the input data.
- Capability inventory: Shell command execution of
blenderand execution of Python code via thebpyandbmeshAPIs. - Sanitization: No explicit sanitization or validation of user-provided parameters is defined within the instructions.
Audit Metadata