skills/nirholas/three.ws/mesh-forge/Gen Agent Trust Hub

mesh-forge

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows standard implementation patterns for AI-assisted 3D generation and provides clear documentation for its functionality and costs.- [INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge for user-provided prompts and external image URLs which are processed by backend AI models. While this represents a standard attack surface for indirect prompt injection, it is inherent to the skill's primary purpose.
  • Ingestion points: The tool accepts prompt, image_url, and image_urls from the user or the environment (SKILL.md).
  • Boundary markers: Not explicitly defined in the prompt templates.
  • Capability inventory: The skill uses the mesh_forge tool to communicate with external model pipelines (Granite, FLUX, TRELLIS).
  • Sanitization: Standard validation of input parameters is expected at the tool/API level.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 04:15 PM
Security Audit — agent-trust-hub — mesh-forge