The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for running Blender headlessly via the command line (e.g., blender --background --python script.py). It specifically highlights the use of the --factory-startup flag, which is a positive security practice as it ensures the environment is clean and prevents the automatic loading of potentially malicious user-configured add-ons or startup scripts.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external 3D data and project files.
Ingestion points: The skill uses bpy.ops.wm.open_mainfile to open Blender scenes and several operators like bpy.ops.wm.obj_import, bpy.ops.import_scene.fbx, and bpy.ops.import_scene.gltf to import 3D models from the file system (documented in SKILL.md).
Boundary markers: Absent. The instructions do not specify any validation or isolation techniques for the content loaded from these external files.
Capability inventory: The skill possesses the capability to write to the file system using os.makedirs, bpy.ops.wm.save_as_mainfile, and various export operators (documented in SKILL.md).
Sanitization: Absent. There is no evidence of filename sanitization or data validation for the assets being processed.

blender-scripting