Open Source · Elastic License 2.0

Five Layers. One Install.
Zero Trust.

The complete security platform for OpenClaw. Blocks prompt injection, supply chain attacks, and credential theft — before they reach your agent.

$
0pattern rules0correlation rules0OpenClaw config changes
500+Detection Rules
AES-256-GCMVault Cipher
<1msProxy Overhead
5Security Layers
0Cloud Dependencies

Threat Landscape — Scanning Active

OpenClaw agents are a new attack surface

Agents browse the web, install skills, and hold your API keys. Every capability is also a vector.

T1

Prompt Injection

CRITICAL

Malicious instructions hidden in web content hijack your agent — redirecting tool calls, leaking memory, and overriding user intent.

T2

Supply Chain Attack

HIGH

A skill with a backdoor runs with full agent permissions. ClawHub scans every package before install.

T3/T6

Data Exfiltration

HIGH

Agent memory silently written to attacker-controlled URLs. ClawGuard intercepts outbound requests and blocks unauthorized exfil.

T7

Credential Theft

CRITICAL

API keys extracted from responses and sent outbound. ClawVault isolates secrets from agent reach.

Defense Architecture — All Systems Online

Defense in depth. Every layer independent.

Five modules. One package. Each layer operates independently — if one fails, the others keep running.

01

ClawBox

HARDENED

Hardened Docker deployment

Docker Compose
02

ClawVault

SEALED

AES-256-GCM credential vault

~/.clawsentinel/vault/
03

ClawGuard

ACTIVE

WS + HTTP proxy firewall

:18790 → :18789
04

ClawHub

WATCHING

Supply chain scanner

hooks openclaw skill install
05

ClawEye

ONLINE

Real-time dashboard

localhost:7432

Passthrough-first design

If ClawSentinel encounters an error, OpenClaw traffic passes through uninterrupted. Zero downtime guarantee.

Architecture

One package. Five layers.
All connected.

Defense in depth

Each layer operates independently. If ClawGuard Proxy misses something, ClawVault still seals your secrets. No single point of failure.

Passthrough-first

If ClawSentinel encounters an error at any layer, OpenClaw traffic passes through unblocked. Your agent never goes dark.

Unified visibility

ClawEye correlates events across all five layers in real time. One dashboard, one alert feed, one source of truth.

View all five modules →
Internet — Threats

T1 Prompt Injection · T2 Supply Chain · T7 Credential Theft · T3/T6 Exfiltration

intercepted at browser
ClawGuard ExtensionBrowser Layer

Scans browser content in real-time before OpenClaw ever touches it.

pattern-filtered payload
ClawGuard Proxy:18790 → :18789

500-rule engine inspects every WS frame and HTTP response. Pro adds LLM semantic analysis.

clean traffic only
OpenClaw Agent:18789

Receives only verified, sanitized traffic. Runs unmodified — zero config changes.

isolated secrets access
ClawVault + ClawHubAES-256-GCM

Credentials sealed with AES-256-GCM. Every skill install intercepted and scanned.

containerized runtime
ClawBoxDocker Compose

Hardened Docker environment. Reduced attack surface. Isolated from host filesystem.

ClawEye
localhost:7432

Monitors all five layers simultaneously. Correlates events, fires alerts, streams the unified event feed.

Getting Started

Three commands. Fully protected.

ClawSentinel auto-detects your OpenClaw config. No changes to existing setup.

01

Install

0x01
clawsentinel — zsh
~ %npm install -g clawsentinel

One package. All five modules included.

02

Initialize & Start

0x02
clawsentinel — zsh
~ %clawsentinel init && clawsentinel start

Auto-detects your OpenClaw config. No edits needed.

03

Protected

0x03
clawsentinel — zsh
ClawEyelocalhost:7432
ClawGuard
ACTIVE
ClawVault
SEALED
ClawHub
WATCHING
ClawBox
HARDENED
Threats blocked0

All five layers active. Dashboard at localhost:7432.

Browser Extension

Catch threats before your agent reads the page.

ClawSentinel Guard is the browser-side layer of your defense stack. It scans web content at the source — inside your browser — before OpenClaw ever processes it. Works alongside the ClawGuard proxy for complete coverage.

Available forChromeEdgeFirefox

Real-time page scanning

Scans every page load for prompt injection patterns before content reaches your agent.

Injection highlighting

Visually marks detected injection attempts directly in the page so you see what the agent would have received.

Toolbar threat badge

Shield icon in your browser toolbar shows the current page threat level at a glance.

Zero data collection

All scanning is local. No page content, URL, or usage data is ever sent to any server.

Offline-capable

Works on the 500-rule pattern engine even when the ClawGuard proxy is not running.

Connects to ClawGuard

When the proxy is active, the extension syncs threat context for deeper correlation in ClawEye.

Get the ExtensionIncluded with ClawSentinel
example.com/article
CS
ClawSentinel Guardv0.7.0

Current Page

example.com/article

Awaiting scan

0%

0

Threats detected

500

Rules applied

0

Injection patterns

0

Malicious links

ClawGuardWAITING
:18790

Pricing

Pattern rules block what we know. Semantic intelligence blocks what we don't.

Free covers all known threats forever. Pro adds the intelligence layer for everything else.

FreePattern Guard
$0/ forever

All five modules. All known threats. Zero config.

Included modules

ClawGuard Proxy
ClawVault
ClawHub Scanner
ClawBox
ClawEye Dashboard
Browser Extension

Matches known signatures only. Novel, rephrased, and zero-day attacks that miss every rule will pass through.

ProSemantic Intelligence
7-day trial
$9/ month

Everything in Free, plus the intelligence layer.

Pro exclusive — on top of Free

Semantic LLM Engine

Understands intent — catches novel, rephrased, and zero-day attacks no pattern rule covers.

BYOK · Anthropic / OpenAI / Ollama

Correlation Engine

Watches all 5 layers simultaneously. Fires when events combine into a multi-stage attack chain.

7 cross-layer rules

Background Token Renewal

Access token refreshed silently every 23 hours. Zero interruptions to your agent.

Silent · 23h cycle
Start 7-day free trial →

No charge for 7 days · Cancel anytime · Access revoked within 24 h

What each plan detects

Attack TypeFreePro
Known injection (rule match)
Blocked
Blocked
Novel / rephrased injection
Missed
Blocked
LLM engine
Polymorphic attack variant
Missed
Blocked
semantic intent
Multi-stage exfiltration
Partial
Blocked
correlation rule
Supply chain + exfil combo
Partial
Blocked
RULE-04 fires
Zero-day technique
Missed
Blocked
LLM intent check

Pro uses your own API key (BYOK). No traffic is processed by ClawSentinel servers.

Elastic License 2.0

Open source. Auditable. Yours.

Every rule, every detection, every line of ClawGuard is public. Licensed under Elastic License 2.0 — free to use, self-host, and audit. No hidden logic. No black-box rules.

The Pro semantic engine uses your own API keys (BYOK) — we never see your traffic or credentials.

audit — clawsentinel

Secure Your Agent Today

Zero Trust protection
in 30 seconds.

No cloud. No data collection. No changes to your OpenClaw config. Just install and start — all five layers activate automatically.

$npm install -g clawsentinel
Free tier includes all 5 modulesNo account requiredOpen source · Auditable