threejs-3d-generator

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches 3D models and preview images from the Tripo AI API (api.tripo3d.ai). These downloads are the primary function of the skill for retrieving generated game assets.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data including user-defined prompts and local asset files which are sent to a remote API.
  • Ingestion points: User input for the --prompt argument in SKILL.md and local files provided to --image or --glb_path in scripts/threejs_3d_asset.py.
  • Boundary markers: None; text prompts are interpolated directly into JSON payloads for the Tripo API.
  • Capability inventory: The script scripts/threejs_3d_asset.py has the ability to read and write files in the project directory and perform network operations to api.tripo3d.ai.
  • Sanitization: Standard GLB parsing is performed using the struct module, but no sanitization is applied to the text prompts.
  • [COMMAND_EXECUTION]: Instructions in SKILL.md direct the agent to execute the provided Python script scripts/threejs_3d_asset.py to perform asset generation and validation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 10:30 PM