A comprehensive security auditing tool for OpenClaw environments that identifies configuration risks and provides interactive remediation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install jason-openclaw-security-scanner
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 jason-openclaw-security-scanner 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 Scanner?
The OpenClaw Security Scanner is a specialized utility designed to safeguard your AI automation ecosystem. It performs deep inspections of configuration files, directory permissions, and sensitive credentials to ensure your Openclaw Skills operate within a secure sandbox. By analyzing operation rules and identifying potential data leaks, this skill helps developers maintain a robust security posture and prevent unauthorized agent actions.
This tool is essential for developers who need to verify their environment against common vulnerabilities. It goes beyond simple detection by offering an interactive repair system that can automatically update configuration rules, adjust file permissions, and protect sensitive keys from being exposed in version control.
OpenClaw Security Scanner Use Cases
- Auditing agent permissions to prevent unauthorized file deletions or modifications.
- Detecting exposed API keys, passwords, or tokens within the project directory.
- Verifying that sensitive directories have the correct chmod permissions to prevent external access.
- Checking if AI agents are running in a restricted sandbox environment versus public exposure.
- Automating the application of security red-line rules in the OpenClaw configuration.
How OpenClaw Security Scanner Works
- Scan Initialization: The scanner parses the local OpenClaw environment, checking configuration files and directory structures.
- Threat Detection: It identifies security gaps such as missing .gitignore entries, over-privileged agents, and exposed credentials.
- Scoring: Based on a 100-point system, it deducts points for vulnerabilities (e.g., -25 for severe risks, -15 for high risks).
- Detailed Reporting: It generates a visual report highlighting specific issues, their severity levels, and whether they are fixable.
- Remediation: Through interactive prompts or CLI flags, the tool applies fixes like adding operation red-lines or updating file permissions.
OpenClaw Security Scanner Setup
Ensure you have the OpenClaw environment and necessary Python dependencies installed. You can trigger the scanner using the following commands:
# Perform a standard security scan and view the report
python3 scripts/scan_security.py
# Run in interactive mode to review and apply fixes manually
python3 scripts/scan_security.py --interactive
# Automatically fix all detectable security issues
python3 scripts/scan_security.py --fix-all
OpenClaw Security Scanner Data Schema & Taxonomy
The scanner evaluates and organizes its findings based on the following taxonomy:
| Category | Check Items | Auto-Fix Capability |
|---|---|---|
| Operation Rules | Delete confirmation rules, restricted actions | Yes (Rule injection) |
| Config Permissions | Sandbox status, public network exposure | Partial |
| File Permissions | Directory and sensitive file access levels | Yes (chmod) |
| Sensitive Info | API Keys, Passwords, Tokens, SSH Keys | Yes (.gitignore) |
| Log Auditing | Error statistics, authentication failures | No (Alert only) |
OpenClaw Security Scanner Advanced Features
- Interactive one-by-one remediation mode for granular control over security changes.
- Automated red-line rule injection to force manual confirmation for destructive agent actions.
- Scoring engine to provide a quantitative health check for your Openclaw Skills.
- Bulk fixing capabilities to instantly resolve multiple permission and configuration errors.
SKILL.md
Loading
Related Openclaw Skills
NEIS School CLI
A specialized CLI tool for retrieving official Korean school information, meal plans, and academic schedules directly from the NEIS OpenAPI.
Position Risk Manager
A professional-grade risk management engine for stock portfolios, focusing on position sizing and exit strategies rather than stock selection.
AI Content Detection
A comprehensive forensic toolkit for verifying the authenticity of text, images, video, and audio to detect AI-generated content and deepfakes.
Model Switcher
A dynamic session management tool that allows users to swap between AI models like GPT, Claude, and Qwen instantly without modifying global configurations.
rainman-translate-book
An AI-driven translation skill that utilizes parallel subagents to convert entire books into multiple languages and formats.
Paper Assistant
An automated research assistant that fetches, filters, and recommends high-value AI agent and reinforcement learning papers from OpenReview and arXiv.
Featured*
