tencent-hunyuan3d

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface where untrusted user data is ingested into the model pipeline.
  • Ingestion points: User-provided text prompts and reference images are accepted to initiate 3D generation.
  • Boundary markers: The instructions do not define delimiters or isolation markers to separate user input from system-level logic.
  • Capability inventory: The skill facilitates local file generation (meshes and textures) and interaction with external model APIs.
  • Sanitization: No data validation or sanitization procedures are described for the input data.
  • [EXTERNAL_DOWNLOADS]: The skill documentation describes fetching model weights and configuration files from Hugging Face and official GitHub repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 01:52 PM
Security Audit — agent-trust-hub — tencent-hunyuan3d