Tork Guardian for OpenClaw

OpenClaw is powerful. Tork makes it safe.

Production-ready security and governance for OpenClaw skills. Detect PII, enforce policies, block dangerous tool calls, and scan skills for vulnerabilities — in one npm install.

$npm install @torknetwork/guardian

Now live on ClawHub — install in one command

$clawhub install tork-guardian
157K+
OpenClaw Users
340+
Suspicious Skills Flagged
3 CVEs
in 3 Days
20ms
Latency
The Problem

OpenClaw Has a Security Problem

Malicious Skills

Hundreds of skills on ClawHub have been flagged for potential data exfiltration, port hijacking, and reverse shell patterns. Installing an unscanned skill may give it broad access to your local network.

No Built-in Governance

OpenClaw has no native PII detection, no policy enforcement, and no audit trail. Every tool call runs with full permissions by default.

Compliance Gap

Regulated industries (healthcare, finance, legal) cannot adopt OpenClaw without governance controls. No compliance receipts means no audit trail.

How It Works

Secure Your OpenClaw Skills in 60 Seconds

1

Install

npm install @torknetwork/guardian

Add Tork Guardian to any OpenClaw skill

2

Configure

const guardian = new TorkGuardian({
apiKey: process.env.TORK_API_KEY!
});

Initialize with your API key

3

Protected

Every LLM request is governed. PII is redacted. Tool calls are validated. Compliance receipts are generated automatically.

Features

Core Tools for AI Governance

PII Redaction

Automatically detect and redact emails, phone numbers, SSNs, credit cards, and 30+ PII patterns before they reach the LLM.

Tool Call Governance

Block dangerous operations like shell_execute, file_delete, and rm -rf. Allow only pre-approved tool calls.

Policy Enforcement

Define strict, standard, or minimal policies. Enforce them consistently across all skills with zero code changes.

Skill Scanner

Scan any OpenClaw skill for vulnerabilities before installation. Get a security score and detailed report.

Port Security

Detect port hijacking, block data exfiltration, prevent reverse shells, and stop cross-skill MITM attacks. Control inbound/outbound ports and enforce domain allowlists per skill.

Compliance Receipts

Cryptographic proof of every governance decision. Audit-ready evidence for SOC 2, HIPAA, and GDPR.

Port Security

The Network Firewall OpenClaw Doesn't Have

OpenClaw skills run on your local machine with full network access. One malicious skill can exfiltrate your data, hijack MCP ports, or open reverse shells. Tork Guardian locks it down.

Port Hijacking Protection

MCP servers listen on predictable localhost ports. Malicious skills can bind the same port first, intercepting all traffic. Tork is designed to detect and help block duplicate port bindings.

Data Exfiltration Blocking

Skills silently sending credentials, conversation history, and PII to attacker servers over outbound connections. Tork is designed to enforce domain allowlists and help block unknown egress.

Reverse Shell Detection

A skill opening a listener on an external-facing port gives attackers persistent remote access to your machine. Tork is designed to detect the bind+exec pattern and terminate it.

Cross-Skill MITM Prevention

Skill A opens port 8080, Skill B connects to it — covert inter-skill communication bypassing all governance. Tork helps isolate skills with per-skill port policies.

Port allowlisting (inbound + outbound)
Egress domain filtering
Private network blocking (10.x, 192.168.x)
TLS enforcement
Connection rate limiting per skill
Code

See It In Action

guardian.ts
import { TorkGuardian } from '@torknetwork/guardian';
 
const guardian = new TorkGuardian({
apiKey: process.env.TORK_API_KEY!,
});
 
// Govern an LLM request — PII is automatically redacted
const result = await guardian.governLLM({
messages: [
{ role: 'user', content: 'Email john@acme.com about the project' },
],
});
// result.governed → "Email [EMAIL_REDACTED] about the project"
 
// Block dangerous tool calls
const decision = guardian.governTool({
name: 'shell_execute',
args: { command: 'rm -rf /' },
});
// decision.allowed → false
// decision.reason → "shell_execute is blocked by policy"
 
// Scan a skill before installing
const report = await guardian.scanSkill('./my-skill');
// report.score → 85/100
// report.findings → [{severity: 'high', rule: 'network-unrestricted'}]
Pricing

Simple, Transparent Pricing

Free

$0/mo
  • 1,000 API calls/month
  • PII redaction
  • Basic policies
  • Community support
Start Free
Most Popular

Starter

$39/mo
  • 50,000 API calls/month
  • Advanced policies
  • Skill scanning
  • Email support
Get Started

Pro

$149/mo
  • 500,000 API calls/month
  • Custom policies
  • Priority support
  • Compliance receipts
  • SSO
Get Started

Need enterprise? Contact us for custom pricing.

Stop Installing Unscanned Skills

Add production-ready security to your OpenClaw skills in under 60 seconds.

$npm install @torknetwork/guardian