develop-web-game

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate development workflow for web games, focusing on incremental implementation and automated verification.
  • [EXTERNAL_DOWNLOADS]: The instructions suggest installing playwright and @playwright/mcp, which are well-known libraries for browser automation and integration with agent platforms.
  • [COMMAND_EXECUTION]: The workflow involves running a local Node.js script (web_game_playwright_client.js) that uses the Playwright library to automate browser sessions. This is the core functionality of the skill and is used for game testing.
  • [DATA_EXFILTRATION]: The automation script writes screenshots, game state JSON, and error logs to a local directory (default: output/web-game). It reads an action payload from a local file. No sensitive file access or unauthorized network operations were detected.
  • [PROMPT_INJECTION]: No patterns attempting to bypass safety filters, override system instructions, or extract prompts were found in the instructions or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 08:25 PM
Security Audit — agent-trust-hub — develop-web-game