blender-reconstruct

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill integrates several local Python scripts into the Blender modeling workflow. These include scripts/manufactured.py for shape fitting, scripts/presentation.py for animation validation, and scripts/blender_runtime.py for environment setup. These scripts are executed via Blender's --python command-line argument to automate the processing and review of 3D candidates.
  • [INDIRECT_PROMPT_INJECTION]: The workflow processes external data sources such as owner corrections, photographs, and architectural plans. While these represent ingestion points for external information, the skill mandates a comparison loop and explicit manifest declarations to verify that generated geometry and renders align with the provided evidence, providing a verification layer for the processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 11:48 AM