Openclaw Browser Automation 1.0.1

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from w...

This package appears to do what it says (automate browsers), but the published metadata omits several important requirements and privacy-impacting behaviors. Before installing or running it: (1) Inspect the package's package.json and dependency list (npm install will fetch unknown code). (2) Be prepared to provide an ANTHROPIC_API_KEY and optionally Browserbase keys; only provide keys you trust the code/provider to use. (3) Understand the tool will create a persistent Chrome profile (.chrome-profile) and save downloads/screenshots under ./agent/, which can store cookies, sessions, and downloaded files — delete these when finished if they contain sensitive data. (4) Running npm link will add a global 'browser' command that executes project code; only do this for code from a trusted source. (5) Note that launching Chrome with remote-debugging on port 9222 exposes a CDP endpoint — ensure it's bound to localhost and not accessible remotely. (6) Because the skill has no provenance/homepage and the registry metadata conflicts with its own docs, treat it as untrusted until the author clarifies the discrepancies or provides the actual package code for review.

Type: OpenClaw Skill Name: openclaw-browser-automation-1-0-1 Version: 1.0.0 The skill bundle provides powerful browser automation capabilities with high-risk features, including persistent session management via a local Chrome profile (.chrome-profile/) and automatic redirection to remote environments (Browserbase) without user prompting. It exhibits suspicious indicators such as launching the browser off-screen for stealth and referencing a non-existent AI model (Claude Haiku 4.5) in REFERENCE.md, alongside a future-dated timestamp in _meta.json. While these capabilities are plausibly needed for the stated purpose, the lack of file type restrictions on downloads and the handling of sensitive API keys warrant a cautious classification.