Playwright Browser Automation

使用 Playwright 库实现快速、可靠的多浏览器页面自动化，支持截图、网络拦截和元素智能等待操作。

This skill appears to be a straightforward Playwright tutorial with two example scripts. Before installing or running: 1) Be aware the SKILL.md recommends running 'pip3 install playwright --break-system-packages' — omit --break-system-packages unless you understand its effects on your system package manager. 2) The examples include techniques for hiding automation characteristics and changing User-Agent headers; those are legitimate for testing but could be abused — use responsibly and in accordance with target site policies. 3) Example scripts write files to /tmp and open browsers locally; run them in a sandboxed environment if you are unsure. 4) No credentials are requested by the skill. If you need stronger assurance, ask the author for provenance or run the examples in an isolated VM/container before using on sensitive systems.

Type: OpenClaw Skill Name: playwright-han Version: 1.1.0 The skill bundle provides a standard implementation of the Playwright browser automation library for web scraping and testing. The documentation (SKILL.md) and Python scripts (test_improved.py, test_playwright.py) contain legitimate examples of browser interaction, such as navigating to Baidu, performing searches, and saving screenshots to /tmp/. No evidence of malicious intent, data exfiltration, or prompt injection was found.