blender-render-and-export

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Blender Python API (bpy) to execute rendering and export tasks in background processes. This functionality is intended and mediated by scripts that wrap standard Blender operations.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs that could be used to influence agent behavior through data ingestion.\n
  • Ingestion points: The output_path, camera_name, and object_names variables in scripts/render_or_export.py and command-line arguments in scripts/inspect_roundtrip.py.\n
  • Boundary markers: The scripts do not use explicit delimiters to separate user-supplied strings from the rest of the prompt context.\n
  • Capability inventory: The skill can create directories and write files to the local system using pathlib and bpy.ops.\n
  • Sanitization: The _owned_output function enforces absolute paths, restricts file extensions to specific formats (e.g., .png, .glb, .usd), and prevents overwriting existing files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 06:06 PM
Security Audit — agent-trust-hub — blender-render-and-export