game-builder-blender-assets

Pass

Audited by Gen Agent Trust Hub on Sep 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is entirely instructional and focuses on the high-definition authoring of 3D assets (meshes, UVs, rigs) for game development. It does not contain executable scripts, network commands, or requests for sensitive data.
  • [SAFE]: All file operations described (writing to 'artifacts/' and updating 'art/LEDGER.md') are standard local project management tasks. No persistence mechanisms or privilege escalation patterns are present.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data via 'locked reference shots' to guide the 3D authoring process.
  • Ingestion points: Reference assets ('locked refs') described in the 'When this skill applies' and 'Pipeline for a 3D hero' sections.
  • Boundary markers: The workflow is constrained by the project's 'art/LOOK.md' and the Orchestrator's turnaround gate.
  • Capability inventory: Headless Blender execution for GLB export and file writes to the local 'artifacts/' directory.
  • Sanitization: Not explicitly defined, as the ingestion involves visual/3D references rather than natural language instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 30, 2026, 06:47 PM