Moltbot Integration

Security guardrails for Moltbot with real-time validation, data leak prevention, and threat detection. Designed as a copilot, not a gatekeeper.

Installation

npm install @sentinelseed/moltbot

Add to your Moltbot config:

{
  "plugins": {
    "sentinel": {
      "level": "watch"
    }
  }
}

Protection Levels

The default watch mode provides full monitoring with zero blocking. Higher levels add protection you can always bypass when needed.

How It Works

Sentinel integrates with Moltbot hooks to provide layered protection:

What Gets Detected

Input Analysis detects prompt injection attempts, jailbreak patterns, role manipulation, and system prompt extraction.

Output Validation catches API keys (OpenAI, Anthropic, AWS), passwords, private keys, tokens, credit card numbers, and SSNs.

Tool Validation blocks destructive commands (rm, drop, truncate), system path access, dangerous network operations, and privilege escalation.

Escape Hatches

When you need to bypass protection:

/sentinel pause 5m          # Pause for 5 minutes
/sentinel allow-once        # Allow next action
/sentinel trust bash        # Trust a tool for the session
/sentinel resume            # Resume protection

Configuration

{
  "plugins": {
    "sentinel": {
      "level": "guard",
      "alerts": {
        "enabled": true,
        "webhook": "https://your-webhook.com/sentinel",
        "minSeverity": "high"
      },
      "ignorePatterns": ["MY_SAFE_TOKEN"],
      "logLevel": "warn"
    }
  }
}

Programmatic API

Hook Factory

import { createSentinelHooks } from '@sentinelseed/moltbot';

const hooks = createSentinelHooks({
  level: 'guard',
  alerts: {
    enabled: true,
    webhook: 'https://your-webhook.com/sentinel'
  }
});

export const moltbot_hooks = {
  message_received: hooks.messageReceived,
  before_agent_start: hooks.beforeAgentStart,
  message_sending: hooks.messageSending,
  before_tool_call: hooks.beforeToolCall,
  agent_end: hooks.agentEnd,
};

Validators

import { validateOutput, validateTool, analyzeInput, getLevelConfig } from '@sentinelseed/moltbot';

const levelConfig = getLevelConfig('guard');

const outputResult = await validateOutput(content, levelConfig);
if (outputResult.shouldBlock) {
  console.log('Blocked:', outputResult.issues);
}

const toolResult = await validateTool('bash', { command: 'ls' }, levelConfig);
const inputResult = await analyzeInput(userMessage);

Escape Manager

import { EscapeManager } from '@sentinelseed/moltbot';

const escapes = new EscapeManager();

escapes.grantAllowOnce('session-id', { scope: 'output' });
escapes.pauseProtection('session-id', { durationMs: 300000 });
escapes.trustTool('session-id', 'bash', { level: 'session' });

Audit Log

import { AuditLog } from '@sentinelseed/moltbot';

const audit = new AuditLog({ maxEntries: 1000 });

const recent = audit.getRecent(10);
const stats = audit.getStats();

CLI Commands

/sentinel status            # Current status
/sentinel level [new]       # View/change level
/sentinel log [count]       # View recent audit entries
/sentinel pause <duration>  # Pause protection
/sentinel resume            # Resume protection
/sentinel allow-once [scope]# One-time bypass
/sentinel trust <tool>      # Trust a tool
/sentinel untrust <tool>    # Revoke trust
/sentinel help              # Show all commands

Links

• npm package
• Moltbot
• Source Repository