threejs-game-ui-designer

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on UI/UX principles for game development and does not contain any executable code, unauthorized network requests, or attempts to access sensitive system information.\n- [PROMPT_INJECTION]: The skill incorporates an attack surface for indirect prompt injection as it is designed to analyze external visual data (screenshots) to inventory game states.\n
  • Ingestion points: Desktop and mobile screenshots provided to the agent for inventorying gameplay and UI states (SKILL.md, references/ui-patterns.md).\n
  • Boundary markers: None explicitly mentioned in the instructions to delimit or warn against instructions potentially embedded within analyzed images.\n
  • Capability inventory: The skill utilizes vendor-specific tools (Mint MCP) for asset production and interaction verification (references/ui-patterns.md).\n
  • Sanitization: The skill does not define specific methods for sanitizing, filtering, or escaping instructions that might be contained within analyzed visual inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 04:58 AM
Security Audit — agent-trust-hub — threejs-game-ui-designer