Agent Browser Clawdbot 0.1.0

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

Security Scan

The skill's instructions and requirements are consistent with a headless browser CLI for agents, but there are small metadata inconsistencies and expected installer/usage risks you should review before installing.

Purpose & Capability

The SKILL.md describes a headless browser CLI (navigation, snapshots, interactions, sessions, state save/load) that matches the declared purpose. One inconsistency: registry metadata owner/slug differ from the _meta.json ownerId/slug, which could indicate repackaging or metadata drift — this is not evidence of maliciousness but worth verifying against the upstream project (GitHub homepage).

Instruction Scope

Runtime instructions are focused on running the 'agent-browser' CLI and using its commands (open, snapshot, click, state save/load, network routing, etc.). These commands legitimately require access to browsing state (cookies/localStorage) and can save/load auth JSON files. Note: snapshots and 'get' commands can capture arbitrary webpage content (including secrets) and 'state save' writes sensitive auth state to disk — expected for a browser tool, but sensitive if misused.

Install Mechanism

The skill is instruction-only (no install spec in the manifest), but SKILL.md directs users to 'npm install -g agent-browser' and to run 'agent-browser install' which downloads Chromium and optionally system deps. Installing an npm package and a Chromium binary is normal for this type of tool but carries standard risks (supply-chain or malicious npm packages).

Credentials

The skill declares no required environment variables or credentials. It mentions an optional AGENT_BROWSER_SESSION env var for session selection, which is proportional. There are no unexplained requests for unrelated credentials or secrets in the instructions.

Persistence & Privilege

Defaults (always: false, user-invocable: true, model invocation allowed) are appropriate. The skill does not request permanent platform-wide presence. Be aware that autonomous invocation combined with a browser automation tool can have wider impact if given permission to run unattended, but that is a platform-level consideration rather than a misalignment within the skill itself.

Assessment

This skill appears to do what it says (a CLI headless browser). Before installing: 1) Verify the npm package and GitHub repository match and are published by the expected maintainer (the registry ownerId differs from the _meta.json ownerId here — check upstream). 2) Be cautious installing npm packages globally and allow the tool to download Chromium only from the official source. 3) Treat snapshots and saved state files (auth.json) as sensitive — they can contain cookies/credentials; store them securely and avoid uploading them to untrusted services. 4) If you will run the agent autonomously, consider running the tool in an isolated environment (container or VM) to limit blast radius. 5) If anything about the publisher, checksum, or repo history looks unfamiliar, investigate further or prefer the official upstream project.

Agent Browser Skill

Fast browser automation using accessibility tree snapshots with refs for deterministic element selection.

Why Use This Over Built-in Browser Tool

Use agent-browser when:

• Automating multi-step workflows
• Need deterministic element selection
• Performance is critical
• Working with complex SPAs
• Need session isolation

Use built-in browser tool when:

• Need screenshots/PDFs for analysis
• Visual inspection required
• Browser extension integration needed

Core Workflow

# 1. Navigate and snapshot
agent-browser open https://example.com
agent-browser snapshot -i --json

# 2. Parse refs from JSON, then interact
agent-browser click @e2
agent-browser fill @e3 "text"

# 3. Re-snapshot after page changes
agent-browser snapshot -i --json

Key Commands

Navigation

agent-browser open <url>
agent-browser back | forward | reload | close

Snapshot (Always use -i --json)

agent-browser snapshot -i --json          # Interactive elements, JSON output
agent-browser snapshot -i -c -d 5 --json  # + compact, depth limit
agent-browser snapshot -s "#main" -i      # Scope to selector

Interactions (Ref-based)

agent-browser click @e2
agent-browser fill @e3 "text"
agent-browser type @e3 "text"
agent-browser hover @e4
agent-browser check @e5 | uncheck @e5
agent-browser select @e6 "value"
agent-browser press "Enter"
agent-browser scroll down 500
agent-browser drag @e7 @e8

Get Information

agent-browser get text @e1 --json
agent-browser get html @e2 --json
agent-browser get value @e3 --json
agent-browser get attr @e4 "href" --json
agent-browser get title --json
agent-browser get url --json
agent-browser get count ".item" --json

Check State

agent-browser is visible @e2 --json
agent-browser is enabled @e3 --json
agent-browser is checked @e4 --json

Wait

agent-browser wait @e2                    # Wait for element
agent-browser wait 1000                   # Wait ms
agent-browser wait --text "Welcome"       # Wait for text
agent-browser wait --url "**/dashboard"   # Wait for URL
agent-browser wait --load networkidle     # Wait for network
agent-browser wait --fn "window.ready === true"

Sessions (Isolated Browsers)

agent-browser --session admin open site.com
agent-browser --session user open site.com
agent-browser session list
# Or via env: AGENT_BROWSER_SESSION=admin agent-browser ...

State Persistence

agent-browser state save auth.json        # Save cookies/storage
agent-browser state load auth.json        # Load (skip login)

Screenshots & PDFs

agent-browser screenshot page.png
agent-browser screenshot --full page.png
agent-browser pdf page.pdf

Network Control

agent-browser network route "**/ads/*" --abort           # Block
agent-browser network route "**/api/*" --body '{"x":1}'  # Mock
agent-browser network requests --filter api              # View

Cookies & Storage

agent-browser cookies                     # Get all
agent-browser cookies set name value
agent-browser storage local key           # Get localStorage
agent-browser storage local set key val

Tabs & Frames

agent-browser tab new https://example.com
agent-browser tab 2                       # Switch to tab
agent-browser frame @e5                   # Switch to iframe
agent-browser frame main                  # Back to main

Snapshot Output Format

{
  "success": true,
  "data": {
    "snapshot": "...",
    "refs": {
      "e1": {"role": "heading", "name": "Example Domain"},
      "e2": {"role": "button", "name": "Submit"},
      "e3": {"role": "textbox", "name": "Email"}
    }
  }
}

Best Practices

1. Always use -i flag - Focus on interactive elements
2. Always use --json - Easier to parse
3. Wait for stability - agent-browser wait --load networkidle
4. Save auth state - Skip login flows with state save/load
5. Use sessions - Isolate different browser contexts
6. Use --headed for debugging - See what's happening

Example: Search and Extract

agent-browser open https://www.google.com
agent-browser snapshot -i --json
# AI identifies search box @e1
agent-browser fill @e1 "AI agents"
agent-browser press Enter
agent-browser wait --load networkidle
agent-browser snapshot -i --json
# AI identifies result refs
agent-browser get text @e3 --json
agent-browser get attr @e4 "href" --json

Example: Multi-Session Testing

# Admin session
agent-browser --session admin open app.com
agent-browser --session admin state load admin-auth.json
agent-browser --session admin snapshot -i --json

# User session (simultaneous)
agent-browser --session user open app.com
agent-browser --session user state load user-auth.json
agent-browser --session user snapshot -i --json

Installation

npm install -g agent-browser
agent-browser install                     # Download Chromium
agent-browser install --with-deps         # Linux: + system deps

Credits

Skill created by Yossi Elkrief (@MaTriXy)

agent-browser CLI by Vercel Labs