meshy-3d-printing

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using Python's subprocess module to detect and launch 3D slicer applications (such as OrcaSlicer, Bambu Studio, and PrusaSlicer) on the user's system. It uses platform-specific commands like open on macOS and direct executable calls on Windows and Linux to pass generated 3D model files to the software.
  • [EXTERNAL_DOWNLOADS]: Downloads 3D model assets in various formats (OBJ, 3MF, GLB) from the vendor's asset hosting service at assets.meshy.ai into local project directories.
  • [DATA_EXFILTRATION]: Transmits user-provided prompts, settings, and image URLs to the vendor's API at api.meshy.ai for processing and model generation.
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface as it processes external data.
  • Ingestion points: User-provided prompts and downloaded 3D model files (OBJ) from the remote API.
  • Boundary markers: Absent; user input and downloaded content are used without explicit delimiters.
  • Capability inventory: Subprocess execution for launching slicers and local file system write access for model post-processing.
  • Sanitization: No evidence of input sanitization or validation for user-provided prompts or downloaded model content before they are processed by the script's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 05:05 PM