A zero-telemetry security auditing CLI and live dashboard for hardening AI agent installations and detecting vulnerabilities.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-security-guard
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openclaw-security-guard using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenClaw Security Guard?
OpenClaw Security Guard serves as the essential security layer for modern AI agent environments. It provides a comprehensive auditing suite designed to scan for exposed secrets, configuration weaknesses, and potential prompt injection vulnerabilities. By integrating this tool into your Openclaw Skills workflow, you can ensure that your automated agents operate within a hardened and secure perimeter.
The tool is built with a privacy-first approach, featuring zero telemetry to ensure that all security scans, API key detections, and configuration audits remain strictly local. Whether you are managing a single instance or a complex multi-agent system, this utility provides the transparency and control needed to mitigate risks associated with LLM-based automation.
OpenClaw Security Guard Use Cases
- Scanning local repositories and environments for hardcoded API keys and tokens.
- Detecting and preventing prompt injection attacks and role hijacking in AI workflows.
- Auditing MCP server installations to ensure only verified and allowlisted services are active.
- Hardening OpenClaw configurations by validating sandbox modes and rate-limiting policies.
- Maintaining a high security posture for all Openclaw Skills through continuous monitoring.
How OpenClaw Security Guard Works
- Installation: Deploy the guard via npm to access the global CLI commands.
- Security Auditing: Run the audit command to perform a deep scan of secrets, dependencies, and configurations.
- Vulnerability Analysis: Review the Security Score and detailed findings provided in the terminal or the live web dashboard.
- Automated Hardening: Execute the fix command to automatically resolve identified issues with built-in backup protection.
- Continuous Monitoring: Launch the dashboard for real-time security tracking of your AI agent environment.
OpenClaw Security Guard Setup
# Install the security guard globally
npm install -g openclaw-security-guard
# Run a full security audit of your environment
openclaw-guard audit
# Automatically fix security vulnerabilities
openclaw-guard fix --auto
# Launch the local security dashboard
openclaw-guard dashboard
OpenClaw Security Guard Data Schema & Taxonomy
| Category | Audit Focus | Technical Detail |
|---|---|---|
| Secrets | API Keys & Tokens | 15+ formats with entropy analysis |
| Configuration | Sandbox & Policies | Validates DM policies and gateway bindings |
| Prompting | Injection Patterns | 50+ patterns for jailbreak detection |
| Dependencies | Node Package Safety | Integrated npm CVE scanning |
| MCP Servers | Server Verification | Allowlist-based server integrity checks |
OpenClaw Security Guard Advanced Features
- Local Live Dashboard: Real-time security monitoring hosted at localhost:18790.
- Security Scoring: A quantitative 0-100 metric to track your installation's security posture over time.
- Pre-commit Hooks: Prevent the accidental commit of secrets before they reach your version control.
- Multi-language Support: Native interface available in English, French, and Arabic.
- Zero Telemetry: Guaranteed 100% local execution with no external network requests for data harvesting.
SKILL.md
Loading
Related Openclaw Skills
Twitter Operations
A full-featured automation and management toolkit for X/Twitter integrated directly into your AI workflow.
Million Bit Homepage Minting Skill
An automated tool to mint images and links as permanent NFT plots on the Million Bit Homepage canvas on the Base blockchain.
Smart Model Switching
A cost-saving routing system that automatically directs tasks to the most efficient Claude model tier based on task complexity.
Coder for OpenClaw
A dedicated coding sub-agent for OpenClaw that handles background execution, test-driven bug fixing, and automated project scaffolding.
Giphy GIF Search
A lightweight integration for AI agents to search and post contextual Giphy GIFs within Discord environments.
chrome-open-tabs
A powerful utility to read and list open browser tabs from Chromium-based browsers, including support for synced mobile and desktop devices.
Featured*
