create-3d-model-from-image
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation provides installation commands for auxiliary setup skills located in the vendor's official GitHub repository (
AgentPMT/agent-skills). - [DATA_EXFILTRATION]: Several actions, such as
create_model_from_image, require external URLs (image_url,texture_image_url) to fetch source content for processing. This is a standard functional requirement for the skill's purpose. - [PROMPT_INJECTION]: The skill ingests user-provided text prompts to generate 3D assets. This creates an attack surface for indirect prompt injection, though the skill includes a
moderationparameter to help screen for harmful content.
Audit Metadata