playwright-testing

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and references (SKILL.md "Record or author tests" and references/playwright.md "Interactive Exploration (Codegen)" and "Using MCP for Exploration") explicitly instruct an agent to navigate to arbitrary target URLs and use Playwright/MCP to read DOM/accessibility trees and generated page content, which are untrusted third-party web pages whose content the agent will interpret to generate tests and drive actions.