add-3d-assets

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as obfuscation, data exfiltration, or unauthorized privilege escalation were detected. The skill's behavior aligns with its stated purpose of game asset enhancement.
  • [EXTERNAL_DOWNLOADS]: Downloads 3D models and props from well-known industry services including Poly Haven and Sketchfab. These are trusted sources for game assets.
  • [COMMAND_EXECUTION]: Executes local scripts provided by the plugin (meshy-generate.mjs and find-3d-asset.mjs) using Node.js to automate model generation and retrieval tasks.
  • [PROMPT_INJECTION]: The skill analyzes local game source code to derive context for 3D asset generation, which presents a surface for indirect prompt injection.
  • Ingestion points: Reads local files including package.json, src/core/Constants.js, and gameplay logic in src/gameplay/*.js and src/entities/*.js.
  • Boundary markers: None identified; the skill assumes the analyzed code is trusted developer source code.
  • Capability inventory: Executes local scripts via subprocesses and writes GLB files and modified JavaScript code to the project directories.
  • Sanitization: No specific sanitization or filtering of ingested source code content is mentioned before it is processed for AI prompt generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:09 PM