blender-3d-asset-generation

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses standard Blender automation practices for asset management. The provided script, scripts/audit_blender_asset.py, is designed for local scene inspection and reporting, with no evidence of data exfiltration or unauthorized system access.\n- [INDIRECT_PROMPT_INJECTION]: The skill manages external 3D assets and image data, creating a potential ingestion surface for indirect prompt injection.\n
  • Ingestion points: Scene data and image file paths are accessed via the bpy API in scripts/audit_blender_asset.py.\n
  • Boundary markers: The instructions mandate establishing an asset contract and using predefined quality gates for validation.\n
  • Capability inventory: The skill's capabilities include scene data inspection and writing local validation reports; it does not perform network operations.\n
  • Sanitization: Untrusted data from scene files is used exclusively for calculating geometric metrics and existence checks rather than being interpolated into executable code or prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:33 PM