The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data via CLI arguments to specify output paths and configuration for rendering tasks.
Ingestion points: Arguments such as --out and --save processed in scripts/render_batch.py and scripts/_bpyx.py.
Boundary markers: No explicit delimiters or "ignore embedded instructions" warnings are present for these inputs.
Capability inventory:
scripts/render_batch.py: Uses os.makedirs to create directories and bpy.ops.render.render to write image or video files to the filesystem.
scripts/_bpyx.py: Uses bpy.ops.wm.save_as_mainfile to save Blender project files to user-specified paths.
Sanitization: Input is parsed using standard argparse types, but there is no explicit validation or restriction on the target file paths.

blender-rendering