When to Use

The skill explicitly uses `npx` and `node` for executing Playwright commands and JavaScript, allowing for arbitrary code execution if the agent is prompted to run malicious scripts or if the installed packages are compromised.

npx @playwright/mcp --headless
npx playwright test
const { chromium } = require('playwright');

The skill lists `browser_evaluate` as a common MCP action, enabling arbitrary JavaScript execution within the context of the browsed page, which can be used for data extraction or DOM manipulation.

`browser_evaluate` for inspection and extraction

The skill installs `playwright` and `@playwright/mcp` via `npm`. A compromise of these packages or their dependencies could lead to the execution of malicious code during installation or subsequent use.

install":[{"id":"npm-playwright","kind":"npm","package":"playwright"},{"id":"npm-playwright-mcp","kind":"npm","package":"@playwright/mcp"}]

The skill's core function involves interacting with and extracting data (e.g., form input, cookies, page content) from user-requested web origins, which could be abused to exfiltrate sensitive information to attacker-controlled domains.

description: "extract data"
External Endpoints: User-requested web origins | Browser requests, form input, cookies, uploads, and page interactions required by the task