configure-ux-testing

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (Step 1: "Use WebSearch or WebWebFetch to verify current versions" pointing to public sites like playwright.dev/npm and Step 10: configuring Playwright MCP in .mcp.json so the agent "can navigate web pages, take screenshots, fill forms, click elements") clearly instructs the agent to fetch and read untrusted public web content that can influence actions.