A read-only security auditor designed to identify misconfigurations, credential leakage, and attack vectors in OpenClaw and Clawdbot deployments.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-security-audit
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-audit 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 Audit?
The OpenClaw Security Audit skill is a specialized diagnostic tool for developers and system administrators to ensure their AI agent infrastructure is secure. It performs comprehensive inspections of host environments, network exposure, and internal configurations to find vulnerabilities like publicly accessible gateways or insecure tool policies.
By leveraging this Openclaw Skills integration, users can generate actionable reports that highlight risks such as Cross-Site WebSocket Hijacking (CSWSH) or improper file permissions without making destructive changes. It adheres to a strict read-only protocol to ensure that the auditing process itself does not introduce instability or exfiltrate sensitive data.
OpenClaw Security Audit Use Cases
- Reviewing the security posture of a new Clawdbot or Moltbot installation to ensure it follows best practices.
- Identifying if the OpenClaw gateway or Control UI is exposed to the public internet without proper authentication.
- Auditing installed Openclaw Skills for supply-chain risks, such as hidden shell commands or untrusted sources.
- Detecting plaintext credentials, tokens, and improper file permissions within the configuration directories.
- Hardening production deployments by reviewing tool execution policies and identifying unnecessary root privileges.
How OpenClaw Security Audit Works
- Identify the host environment, operating system, and containerization status to establish a security context.
- Detect the presence of active gateway processes and record version numbers to check against known CVEs.
- Scan network interfaces and listening services to identify unauthorized public access to common internal ports.
- Analyze gateway configuration files for bind addresses, authentication settings, and reverse proxy trust configurations.
- Evaluate tool execution policies and skill permissions to identify potential unauthorized shell command execution vectors.
- Generate a structured terminal report categorized by status (OK, VULNERABLE, or UNKNOWN) with specific remediation steps for every finding.
OpenClaw Security Audit Setup
To use the security audit skill within your environment, ensure you have the OpenClaw CLI installed and then add the skill to your local registry.
openclaw skill install openclaw-security-audit
Run the audit by prompting your agent with a natural language command:
# Example prompt
"Run a full security audit on this OpenClaw deployment and provide a vulnerability report."
OpenClaw Security Audit Data Schema & Taxonomy
The skill organizes its findings into a standardized audit report format. It analyzes the following metadata and file structures to generate its report:
| Category | Data Points Analyzed |
|---|---|
| Environment | Hostname, OS version, Kernel version, Virtualization type |
| Network | Listening ports, Gateway bind address (localhost vs. public) |
| Config | ~/.openclaw/config.json, Gateway mode, Authentication tokens |
| Permissions | ~/.openclaw file permissions, SUID/SGID binaries, Cron jobs |
| Logs | systemd journal logs, gateway access logs, failed auth attempts |
OpenClaw Security Audit Advanced Features
- Read-only auditing mode that prioritizes system stability while scanning for vulnerabilities.
- Automated detection of CSWSH (Cross-Site WebSocket Hijacking) risks in older gateway versions.
- Comprehensive supply-chain analysis of third-party Openclaw Skills to detect hidden malicious instructions.
- Privilege escalation detection by identifying risky binaries and unnecessary sudo configurations.
- Interactive remediation support where the agent can propose and execute fix commands upon explicit user approval.
SKILL.md
Loading
Related Openclaw Skills
Clawstrike Security Audit
A comprehensive security auditing tool designed to identify misconfigurations and attack paths within OpenClaw deployments.
ClawdStrike
A comprehensive security audit and threat modeling tool designed to verify the integrity and safety of OpenClaw gateway hosts.
Clawstrike Security Audit
A specialized security auditing tool that produces deterministic vulnerability reports and threat models for Openclaw gateway environments.
Lore Knowledge Base
A sophisticated research repository skill that enables AI agents to ingest, search, and synthesize knowledge with full source citations.
Skill Vetter
A security-first auditing tool designed to analyze and vet AI agent skills for malicious patterns and dangerous permissions before installation.
Factory AI Droid CLI
A high-performance software engineering agent that integrates with Openclaw Skills to build, debug, and deploy code via the droid CLI.
Google Home / Nest CLI
A command-line interface to manage Google Nest devices using the Smart Device Management API.
Featured*
