← Back to Skills Marketplace
31719
Downloads
57
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install playwright-scraper-skill
Description
Playwright-based web scraping OpenClaw Skill with anti-bot protection. Successfully tested on complex sites like Discuss.com.hk.
Usage Guidance
Install only if you need this exact scraping capability and can run it in an isolated environment. Use it only on sites you are authorized to access, avoid authenticated or sensitive pages, keep screenshot/HTML outputs in a dedicated directory, and do not follow the optional deep-scraper install path unless you separately review and pin that dependency.
Capability Analysis
Type: OpenClaw Skill
Name: playwright-scraper-skill
Version: 1.2.0
The skill is designed for web scraping, including bypassing anti-bot measures using Playwright. While the core functionality and documentation are aligned with its stated purpose, the `scripts/playwright-stealth.js` file uses the `--no-sandbox` and `--disable-setuid-sandbox` flags when launching Chromium. Disabling the browser's sandbox is a security risk, as it can make the system more vulnerable if the browser itself is compromised by malicious web content. Although this is a common practice in web scraping for compatibility, it represents a risky capability without clear malicious intent from the skill author, thus classifying it as suspicious.
Capability Assessment
Credentials
The stealth script launches Chromium with --no-sandbox, --disable-setuid-sandbox, and disabled site isolation while visiting arbitrary websites, which is disproportionate for routine scraping and increases host compromise impact if a browser exploit is encountered.
Install Mechanism
Installation uses npm and Playwright with a lockfile present, but documentation repeatedly uses unpinned npx commands and optionally tells users to install and run a separate deep-scraper skill without pinning or audit-boundary warnings.
Instruction Scope
Instructions recommend stealth scraping for Cloudflare/403 cases and suggest proxies, future cookies, and CAPTCHA handling, but do not clearly require authorization, legal/ToS review, privacy handling, or target allowlisting.
Persistence & Privilege
No system persistence, credential theft, or background service was found, but the scripts can write screenshots and optional HTML to caller-controlled paths and the stealth script saves screenshots by default, which is broader local file mutation than necessary without path containment.
Purpose & Capability
The stated purpose is Playwright web scraping with anti-bot/stealth behavior, and the scripts do implement that purpose. The concern is that arbitrary URL navigation, anti-bot evasion, screenshot/HTML capture, and default stealth use create high-impact misuse and host-network exposure without meaningful scoping or warnings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install playwright-scraper-skill - After installation, invoke the skill by name or use
/playwright-scraper-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
Initial ClawHub release: Pure Playwright with anti-bot protection, bilingual docs (EN/ZH), successfully tested on Discuss.com.hk
Metadata
Frequently Asked Questions
What is Playwright Scraper Skill?
Playwright-based web scraping OpenClaw Skill with anti-bot protection. Successfully tested on complex sites like Discuss.com.hk. It is an AI Agent Skill for Claude Code / OpenClaw, with 31719 downloads so far.
How do I install Playwright Scraper Skill?
Run "/install playwright-scraper-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Playwright Scraper Skill free?
Yes, Playwright Scraper Skill is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Playwright Scraper Skill support?
Playwright Scraper Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Playwright Scraper Skill?
It is built and maintained by waisimon (@waisimon); the current version is v1.2.0.
More Skills