Playwright Cli Skills

Automate browser interactions, test web pages and work with Playwright tests.

This skill appears to do what it says: automate Playwright-driven browser interactions and includes an Amazon scraping helper. Before installing or running it, consider: 1) Playwright CLI and Node must already be installed on your machine. 2) The amazon-search scripts load a local storage-state/auth file (e.g., ~/amazon-auth.json or a project-specific path) and will use cookies/storage from it — those files can contain session tokens; only use auth state you trust and remove it after use. 3) The skill and its docs expose run-code and routing features that can execute arbitrary JS in pages and capture network/request bodies and cookies (use isolated browser sessions or a throwaway profile if you are concerned). 4) The included scripts run local shell commands and write CSV/traces to your home directory; review the JS and shell files before running them and run in a sandboxed account or VM if you need extra safety. If you want, I can point out the exact lines that load auth files, execute shell commands, and write output so you can review them quickly.

Type: OpenClaw Skill Name: playwright-cli-skills Version: 1.0.0 The bundle provides a comprehensive toolkit for browser automation using a 'playwright-cli' wrapper, including specific scripts for Amazon product search and data extraction. The scripts (amazon-search.sh and amazon-search.js) utilize local session state files (~/amazon-auth.json) to maintain authentication and execute JavaScript within the browser context to scrape product details into CSV files. While these tools possess high-risk capabilities such as arbitrary code execution in the browser and access to session cookies, their behavior is entirely consistent with the stated purpose of web automation and scraping. No evidence of data exfiltration, malicious persistence, or deceptive prompt injection was found in the code or documentation (SKILL.md, README.md).