Playwright Mcp 1.0.0

Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automat...

This skill appears to be what it claims: a Playwright MCP front-end. Before installing, consider these practical security steps: (1) Verify the npm package (@playwright/mcp) is the expected upstream and review its release page; (2) Restrict the MCP server with --allowed-hosts and avoid using --no-sandbox or --ignore-https-errors unless necessary; (3) Treat browser_evaluate and file-upload tools as sensitive: do not allow the agent to execute arbitrary JS on pages that handle secrets or to upload local files you don't trust; (4) Run the MCP server in an isolated environment (container/VM) if you will automate untrusted sites or internal networks; (5) Monitor network activity and outputs produced in --output-dir. These mitigations address the legitimate but powerful capabilities of browser automation; the skill itself is coherent with its description.

Type: OpenClaw Skill Name: playwright-mcp-1-0-0 Version: 1.0.0 This skill bundle provides browser automation capabilities via the Playwright MCP server. The `SKILL.md` transparently describes the tools and configuration options, including security features like host validation, sandboxing, and restricted file system access. The `examples.py` script is purely illustrative and does not execute any commands. There is no evidence of malicious prompt injection, data exfiltration, unauthorized execution, or persistence mechanisms within the provided files. The capabilities, while powerful (e.g., arbitrary JavaScript execution via `browser_evaluate`), are aligned with the stated purpose of browser automation, and the documentation even addresses security considerations.