text-to-3d-asset-generation
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructs the agent to generate an authoring script for 3D assets and execute it as part of the validation workflow. This is consistent with its primary purpose of asset creation.- [COMMAND_EXECUTION]: Provides instructions to execute shell commands using the
uvtool to run a local script (tools/scripts/view_usd.py) for rendering and screenshotting generated assets.- [INDIRECT_PROMPT_INJECTION]: The skill ingests a text asset name from the user to drive the generation process. This is a minimal ingestion point with no complex data processing identified. - Ingestion points: User-provided text asset name (SKILL.md).
- Boundary markers: Not explicitly defined.
- Capability inventory: Local command execution via
uv run(SKILL.md). - Sanitization: Not explicitly defined.
Audit Metadata