skill test

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 co...

Security Scan

The skill's instructions are coherent with a browser-automation tool, but there are several mismatches and omissions (missing declared binaries, conflicting Rust/Node descriptions) and the runtime commands grant high-capability access to pages, cookies, storage, files and network that you should review before installing or invoking autonomously.

Purpose & Capability

The SKILL.md describes a browser automation CLI (navigate, snapshot, click, fill, network routing, cookies/storage, screenshots, uploads), which aligns with the skill name and description. However, the description claims a Rust-based CLI with a Node fallback while the instructions only show Node/npm/pnpm installation paths; the declared required binaries list only node and npm but the text references git and pnpm (and a GitHub repo). The mismatch between 'Rust-based' and the entirely Node/npm-based install instructions and the omission of git/pnpm from the required-bins list is an inconsistency.

Instruction Scope

The SKILL.md instructs the agent to run CLI commands that will read and manipulate web pages, cookies, localStorage, upload files, take screenshots (to stdout or files), record video, and intercept/mock network requests. Those actions are consistent with browser automation, but they are high-privilege within that domain: the tool can access session cookies, page DOM, and local files (via uploads), and can intercept or mock network traffic — all of which may expose sensitive data if misused. The instructions do not ask the agent to read unrelated local system configuration or environment variables, which is good, but they give broad discretion to interact with arbitrary pages and data.

Install Mechanism

There is no formal install spec in the skill bundle (instruction-only), so the SKILL.md's install instructions are the only guidance. Those recommend npm -g install, a git clone from github.com/vercel-labs/agent-browser, and pnpm build. GitHub is a common source, but the skill omits declaring git and pnpm as required binaries. Because installation is manual (no packaged install spec), the risk depends on whether you actually run those commands — installing global npm packages and building from source can execute arbitrary code, so inspect the upstream repository before installing.

Credentials

The skill declares no required environment variables or credentials, which is proportionate for a CLI that operates via interactive commands. However, the CLI exposes commands to set HTTP basic auth credentials, headers, and to upload files — these are functional needs but may prompt you to supply secrets at runtime. The main proportionality issue is missing declared binaries (pnpm, git) relative to the install instructions, not the presence of unexplained credential requests.

Persistence & Privilege

always:false and no install spec means the skill does not request forced permanent inclusion or elevated platform privileges. The skill does not attempt to modify other skills or agent-wide settings in the provided instructions.

What to consider before installing

This skill appears to be a legitimate browser-automation CLI, but there are a few red flags and high-capability behaviors you should consider before installing or letting an agent use it autonomously: - Mismatched metadata: the description mentions Rust but the instructions show only Node/npm/pnpm; the SKILL.md references git and pnpm yet the skill's required-bins list omits them. Verify the real upstream project (inspect https://github.com/vercel-labs/agent-browser) before running install commands. - High privileges within web context: the CLI can read cookies/localStorage, take screenshots, record video, upload local files, and intercept/mock network requests. These are normal for browser automation but also let the tool access or exfiltrate sensitive session data if misused. - Installation risk: npm -g and building from source execute code on your machine. Only install from a trusted repository and review the package source (especially preinstall/build scripts) before running global installs. - Operational controls: avoid running this skill with sensitive accounts or files unless you sandbox it; do not provide secrets or local files unless necessary; prefer to run installs in a disposable environment (container/VM) and limit autonomous invocation if you are unsure. If you can, ask the publisher for a canonical homepage/release URL and verify the repository and package contents; if you plan to use it, validate the exact binary requirements (git, pnpm, node) and inspect build scripts before installing.

Browser Automation with agent-browser

Installation

npm recommended

npm install -g agent-browser
agent-browser install
agent-browser install --with-deps

From Source

git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
agent-browser install

Quick start

agent-browser open <url>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

Core workflow

1. Navigate: agent-browser open <url>
2. Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
3. Interact using refs from the snapshot
4. Re-snapshot after navigation or significant DOM changes

Commands

Navigation

agent-browser open <url>      # Navigate to URL
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser

Interactions (use @refs from snapshot)

agent-browser click @e1           # Click
agent-browser dblclick @e1        # Double-click
agent-browser focus @e1           # Focus element
agent-browser fill @e2 "text"     # Clear and type
agent-browser type @e2 "text"     # Type without clearing
agent-browser press Enter         # Press key
agent-browser press Control+a     # Key combination
agent-browser keydown Shift       # Hold key down
agent-browser keyup Shift         # Release key
agent-browser hover @e1           # Hover
agent-browser check @e1           # Check checkbox
agent-browser uncheck @e1         # Uncheck checkbox
agent-browser select @e1 "value"  # Select dropdown
agent-browser scroll down 500     # Scroll page
agent-browser scrollintoview @e1  # Scroll element into view
agent-browser drag @e1 @e2        # Drag and drop
agent-browser upload @e1 file.pdf # Upload files

Get information

agent-browser get text @e1        # Get element text
agent-browser get html @e1        # Get innerHTML
agent-browser get value @e1       # Get input value
agent-browser get attr @e1 href   # Get attribute
agent-browser get title           # Get page title
agent-browser get url             # Get current URL
agent-browser get count ".item"   # Count matching elements
agent-browser get box @e1         # Get bounding box

Screenshots & PDF

agent-browser screenshot          # Screenshot to stdout
agent-browser screenshot path.png # Save to file
agent-browser screenshot --full   # Full page
agent-browser pdf output.pdf      # Save as PDF

Video recording

agent-browser record start ./demo.webm    # Start recording (uses current URL + state)
agent-browser click @e1                   # Perform actions
agent-browser record stop                 # Stop and save video
agent-browser record restart ./take2.webm # Stop current + start new recording

Recording creates a fresh context but preserves cookies/storage from your session. If no URL is provided, it automatically returns to your current page. For smooth demos, explore first, then start recording.

Wait

agent-browser wait @e1                     # Wait for element
agent-browser wait 2000                    # Wait milliseconds
agent-browser wait --text "Success"        # Wait for text
agent-browser wait --url "/dashboard"    # Wait for URL pattern
agent-browser wait --load networkidle      # Wait for network idle
agent-browser wait --fn "window.ready"     # Wait for JS condition

Mouse control

agent-browser mouse move 100 200      # Move mouse
agent-browser mouse down left         # Press button
agent-browser mouse up left           # Release button
agent-browser mouse wheel 100         # Scroll wheel

Semantic locators (alternative to refs)

agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "[e-mail]"
agent-browser find first ".item" click
agent-browser find nth 2 "a" text

Browser settings

agent-browser set viewport 1920 1080      # Set viewport size
agent-browser set device "iPhone 14"      # Emulate device
agent-browser set geo 37.7749 -122.4194   # Set geolocation
agent-browser set offline on              # Toggle offline mode
agent-browser set headers '{"X-Key":"v"}' # Extra HTTP headers
agent-browser set credentials user pass   # HTTP basic auth
agent-browser set media dark              # Emulate color scheme

Cookies & Storage

agent-browser cookies                     # Get all cookies
agent-browser cookies set name value      # Set cookie
agent-browser cookies clear               # Clear cookies
agent-browser storage local               # Get all localStorage
agent-browser storage local key           # Get specific key
agent-browser storage local set k v       # Set value
agent-browser storage local clear         # Clear all

Network

agent-browser network route <url>              # Intercept requests
agent-browser network route <url> --abort      # Block requests
agent-browser network route <url> --body '{}'  # Mock response
agent-browser network unroute [url]            # Remove routes
agent-browser network requests                 # View tracked requests
agent-browser network requests --filter api    # Filter requests

Tabs & Windows

agent-browser tab                 # List tabs
agent-browser tab new [url]       # New tab
agent-browser tab 2               # Switch to tab
agent-browser tab close           # Close tab
agent-browser window new          # New window

Frames

agent-browser frame "#iframe"     # Switch to iframe
agent-browser frame main          # Back to main frame

Dialogs

agent-browser dialog accept [text]  # Accept dialog
agent-browser dialog dismiss        # Dismiss dialog

JavaScript

agent-browser eval "document.title"   # Run JavaScript

State management

agent-browser state save auth.json    # Save session state
agent-browser state load auth.json    # Load saved state

Example: Form submission

agent-browser open https://example.com/form
agent-browser snapshot -i
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]

agent-browser fill @e1 "[e-mail]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

Example: Authentication with saved state

# Login once
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "username"
agent-browser fill @e2 "password"
agent-browser click @e3
agent-browser wait --url "/dashboard"
agent-browser state save auth.json

# Later sessions: load saved state
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard

Sessions (parallel browsers)

agent-browser --session test1 open site-a.com
agent-browser --session test2 open site-b.com
agent-browser session list

JSON output (for parsing)

Add --json for machine-readable output:

agent-browser snapshot -i --json
agent-browser get text @e1 --json

Debugging

agent-browser open example.com --headed              # Show browser window
agent-browser console                                # View console messages
agent-browser console --clear                        # Clear console
agent-browser errors                                 # View page errors
agent-browser errors --clear                         # Clear errors
agent-browser highlight @e1                          # Highlight element
agent-browser trace start                            # Start recording trace
agent-browser trace stop trace.zip                   # Stop and save trace
agent-browser record start ./debug.webm              # Record from current page
agent-browser record stop                            # Save recording
agent-browser --cdp 9222 snapshot                    # Connect via CDP

Troubleshooting

• If the command is not found on Linux ARM64, use the full path in the bin folder.
• If an element is not found, use snapshot to find the correct ref.
• If the page is not loaded, add a wait command after navigation.
• Use --headed to see the browser window for debugging.

Options

• --session <name> uses an isolated session.
• --json provides JSON output.
• --full takes a full page screenshot.
• --headed shows the browser window.
• --timeout sets the command timeout in milliseconds.
• --cdp <port> connects via Chrome DevTools Protocol.

Notes

• Refs are stable per page load but change on navigation.
• Always snapshot after navigation to get new refs.
• Use fill instead of type for input fields to ensure existing text is cleared.

Reporting Issues

• Skill issues: Open an issue at https://github.com/TheSethRose/Agent-Browser-CLI
• agent-browser CLI issues: Open an issue at https://github.com/vercel-labs/agent-browser