CBrowser's most unique feature. No other browser automation tool has built-in ethical boundaries.

The Problem

Other AI automation tools will execute any command you give them:

"Click Delete All Data" ✅ Done
"Submit this $10,000 transfer" ✅ Done
"Accept all terms and conditions" ✅ Done

This is dangerous. AI agents can be tricked, make mistakes, or misread context.

The Solution: Action Zones

CBrowser classifies every action into one of five safety zones:

Zone	Color	Actions	Behavior
Green	🟢	Navigate, read, screenshot, scroll	Auto-execute immediately
Yellow	🟡	Click buttons, select options	Log and proceed
Orange	🟠	Fill forms, smart-click, session management, persona creation, cognitive journeys	Allowed with caution warning
Red	🔴	Submit forms, delete, purchase, account changes	Requires verification
Black	⬛	Bypass authentication, inject scripts, violate ToS	Never executes

How It Works

Green Zone (Safe)

These actions cannot cause harm:

# All auto-execute without prompts
npx cbrowser navigate "https://example.com"
npx cbrowser screenshot
npx cbrowser extract "all product names"

Yellow Zone (Logged)

Interactive but low-risk actions:

# Executes but logs the action
npx cbrowser click "Add to Cart"

Every yellow action is logged with:

Timestamp
Action type
Target element
Screenshot before/after

Orange Zone (State-Modifying)

Actions that modify state but are generally safe:

# Proceeds with caution message
npx cbrowser fill "email" "[email protected]"
npx cbrowser smart-click "Sign In"
npx cbrowser session save "my-session"

Orange zone covers: form fills, smart clicks, session management, persona creation, cognitive journeys, test generation/repair, and marketing tools.

Red Zone (Verification Required)

Potentially destructive or irreversible:

# Will prompt for confirmation
npx cbrowser click "Delete Account"
npx cbrowser click "Place Order"
npx cbrowser click "Submit Application"

To bypass verification (use carefully):

npx cbrowser click "Delete Account" --force

Black Zone (Never Allowed)

CBrowser will refuse these actions entirely:

Attempting to bypass login screens
Injecting JavaScript into pages
Automating CAPTCHA solving
Violating robots.txt
Scraping personal data without consent

npx cbrowser inject-script "alert('hacked')"
# Error: Action blocked by constitutional safety rules

The Five Laws

CBrowser follows five constitutional principles:

1. Transparency

Every action is logged with timestamps and screenshots. You can always review what happened.

# View audit log
npx cbrowser audit --last 50

2. Verification

Destructive actions need explicit confirmation. No accidental deletions.

3. Privacy

Credentials are never logged
Personal data is automatically redacted in logs
Screenshots blur sensitive fields

4. Politeness

Respects robots.txt
Adds delays between actions (no flooding servers)
Identifies itself as automation (never pretends to be human)

5. Fallback

When uncertain, CBrowser asks. When dangerous, it stops.

Configuration

Adjusting Zone Classifications

Create .cbrowserrc.json:

{
  "safety": {
    "redZoneActions": [
      "delete",
      "remove",
      "purchase",
      "submit",
      "transfer"
    ],
    "blacklistPatterns": [
      "admin/*",
      "*/delete-all"
    ],
    "requireVerification": true
  }
}

Disabling Safety (Not Recommended)

For testing environments only:

CBROWSER_UNSAFE=true npx cbrowser click "Delete Everything"

⚠️ Warning: This disables all safety checks. Use only in isolated test environments.

Why This Matters

As AI agents become more autonomous, safety becomes critical:

Mistakes happen - AI can misinterpret commands
Attacks happen - Prompt injection can manipulate agents
Context is lost - Agents don't understand consequences

Constitutional safety limits damage even when things go wrong.

Persona Testing - Another unique CBrowser feature
CLI Reference - See --force flag documentation
FAQ - Common safety questions

Copyright: (c) 2026 Alexa Eden.

License: MIT License

Contact: [email protected]

Constitutional Safety