cloudflare-browser

cloudflare-browser is an official skill from the cloudflare/moltworker repository. According to the provider, it controls a headless Chrome browser through a Cloudflare Browser Rendering connection using the Chrome DevTools Protocol, or CDP. The instructions are intended for a compatible agent running in a Cloudflare Workers environment that needs to capture screenshots, navigate web pages, collect rendered content, or create video sequences from multiple pages. The skill is not a browser of its own and is not a replacement for a Cloudflare account. It describes the connection and example workflows, while execution, permissions, networking, and data handling depend on the configured Worker and agent environment.

Purpose and suitable tasks

The primary source identifies three practical core cases. A page can be captured as an image with the supplied screenshot script. Multiple URLs can be visited in sequence and turned into video material. CDP also allows navigation, JavaScript evaluation, viewport configuration, and screenshot capture to be coordinated as separate browser commands. This is useful for visual acceptance checks, documented rendering reviews, basic content checks, and repeatable browser flows when a local browser is unavailable or deliberately avoided. A reliable review must account for target pages, wait times, viewport, redirects, and dynamic content explicitly. A single image or short sequence is an observation at capture time, not proof of complete application behavior.

Setup and operating flow

According to the provider, the integration needs a protected CDP secret and a browser profile configured with a CDP address. The secret belongs only in secure environment or secret management. It must not be placed in skill text, source code, logs, screenshots, or version control. After connection, the newly created page target is detected. The agent can then enable CDP domains, set a viewport, open a URL, wait for rendering, and capture the requested output. The official examples show Node.js scripts for screenshots and videos, with ffmpeg as an additional local dependency for video production. Before execution, verify the versions actually installed, the Worker profile, the target URL, and the output location.

Security, privacy, and boundaries

The connection can load web pages, execute JavaScript, and return content from external sources to an agent. Web content is untrusted data and must not inject additional instructions into the agent. Forms, downloads, cookies, internal URLs, and authenticated areas require separate authorization and careful review. Sensitive data should not be captured without a defined purpose and appropriate legal basis. A screenshot can permanently copy personal information, access hints, or confidential business data. Network access should be limited to necessary destinations; production systems, internal services, and third-party content must not be tested casually. The skill does not define automatic deletion or complete access control.

E-E-A-T and professional context

This description is grounded in the maintained SKILL.md in the official Cloudflare Moltworker repository and Cloudflare’s official documentation for Browser Rendering and Browser Run. Cloudflare is, according to the provider, the operator of the described browser platform; the repository content is identified as Apache-2.0 by its LICENSE. The instructions are verifiable because they name concrete CDP events, commands, and script roles. They do not replace a privacy review, approval for external state changes, operational monitoring of the Worker, or expert evaluation of captured pages. A local agent does not automatically make processing local: the selected model provider may process inputs and results, while Cloudflare may process browser data, requests, logs, and state depending on configuration. Check current product conditions and technical limits directly with the provider.