threejs-pro

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill involves loading and processing external 3D model files (GLTF/GLB). While these are standard data formats for web graphics, they constitute an ingestion surface for external data.
  • Ingestion points: The useGLTF hook is used to load external model files in SKILL.md.
  • Boundary markers: None explicitly defined for model metadata or embedded strings.
  • Capability inventory: The skill uses standard CLI tools (npm, gltf-transform) for package management and asset optimization.
  • Sanitization: Relies on standard loaders (@react-three/drei) which perform typical parsing of binary and JSON geometry data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 02:47 PM