3d-asset-generation
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and processing data from external 3D generation providers.\n
- Ingestion points: 3D artifacts and metadata are retrieved from external tools such as
atlas_3d,fal_3d, andthreejs_asset_catalogas specified in SKILL.md.\n - Boundary markers: The instructions do not define explicit delimiters or boundary markers to isolate potentially untrusted metadata from the agent's core instruction set.\n
- Capability inventory: The agent utilizes the
blender_worldtool for mesh inspection and scene assembly, which involves executing scripts within a Blender environment and managing files on the system.\n - Sanitization: There is no mention of sanitizing or validating metadata or parameters retrieved from generation providers before they are logged in the asset provenance manifest.
Audit Metadata