skills/openai/plugins/game-playtest/Gen Agent Trust Hub

game-playtest

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFE
Full Analysis
  • Standard Tool Integration: The skill recommends using Playwright for browser automation and SpectorJS for WebGL debugging. These are industry-standard tools for frontend and game development QA. Their use here aligns with the skill's primary objective of visual and functional verification and follows established project testing workflows.
  • Indirect Prompt Injection Surface: As a tool that interacts with external browser content and game scenes, there is a theoretical surface for indirect prompt injection (Ingestion points: Game UI, canvas, and DOM via Playwright in SKILL.md; Boundary markers: Not explicitly defined; Capability inventory: Browser automation and visual capture; Sanitization: None specified). However, this is a standard risk for any browser-based automation tool and is contextually appropriate for the skill's intended purpose.
  • Local Resource Referencing: The skill references other documentation and skills using relative local file paths (e.g., ../web-game-foundations/SKILL.md). This is a standard practice for modular skill design within a repository and does not involve external network requests or remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 01:26 PM