browser-cdpReal Chrome browser automation via CDP Proxy — access pages with full user login state, bypass anti-bot detection, perform interactive operations (click/fill...
Install via ClawdBot CLI:
clawdbot install 0xcjl/browser-cdpGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://localhost:3456/eval?target=TARGET_IDCalls external URL not in known-safe list
http://127.0.0.1:9222/json/versionAI Analysis
The skill interacts only with local services (Chrome CDP on port 9222 and a local proxy on port 3456) for its stated automation purpose. The 'UNKNOWN_DATA_SINK' signal is a false positive, as the endpoint is the skill's own local proxy. No evidence of credential harvesting, hidden instructions, or external data exfiltration exists.
Audited Apr 16, 2026 · audit v1.0
Generated May 9, 2026
Extract data from search result pages (Google, Bing, YouTube) that block static fetchers. The skill bypasses anti-bot measures and captures JavaScript-rendered content, enabling retrieval of search rankings, ad information, and video metadata.
Access and extract private content from platforms like YouTube, Twitter/X, Xiaohongshu, and WeChat public accounts using the user's full login state. Ideal for gathering analytics, monitoring competitors, or aggregating subscriber-only material.
Perform complex web interactions such as clicking buttons, filling forms, scrolling, and dragging elements. Useful for testing web applications, automating data entry, or interacting with dynamic web UIs that require real user actions.
Take high-quality screenshots of any web page at any point during navigation, including after JavaScript rendering or user interactions. Valuable for visual monitoring, compliance records, or UI testing.
Scrape content from websites that employ advanced anti-bot measures like CAPTCHAs or request interception. By using a real Chrome browser session, the skill mimics human behavior and successfully retrieves blocked data.
Provide pre-scraped, cleaned datasets from platforms that are difficult to access (e.g., social media analytics, e-commerce prices). Customers subscribe to receive regular updates without needing to manage scraping infrastructure.
Offer a managed API that handles browser interactions for clients (e.g., form filling, screenshot capture, content extraction). Clients pay per operation or via a monthly retainer for integration support.
Enable web developers and QA teams to run automated tests on dynamic websites. The platform provides real browser interactions and screenshots, with pricing based on test runs or concurrent sessions.
💬 Integration Tip
Ensure Chrome is launched with the specified debugging flags and the CDP proxy service is running. Use the provided API endpoints directly or wrap them in a simple script to automate multi-step workflows.
Scored May 9, 2026
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
Uses a headless browser to navigate web pages, interact with elements, and extract clean, readable text content from URLs.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
通过已登录的Edge或Chrome浏览器，利用Chrome DevTools Protocol执行JS渲染页面的导航、点击、截图及数据提取等自动化操作。
High-performance browser automation for heavy scraping, multi-tab management, and precise DOM extraction. Use this when you need speed, reliability, or advanced state management (cookies/local storage) beyond standard web fetching.
Ultimate stealth browser automation with anti-detection, Cloudflare bypass, CAPTCHA solving, persistent sessions, and silent operation. Use for any web automation requiring bot detection evasion, login persistence, headless browsing, or bypassing security measures. Triggers on "bypass cloudflare", "solve captcha", "stealth browse", "silent automation", "persistent login", "anti-detection", or any task needing undetectable browser automation. When user asks to "login to X website", automatically use headed mode for login, then save session for future headless reuse.