Our review
ClawGuard is a security layer that intercepts and controls shell commands, file operations, and network requests made by an AI assistant based on a customizable policy.
Strengths
- Deny-by-default policy minimizes attack surface.
- Fail-closed behavior ensures security on errors.
- Supports manual approval for high-risk actions.
Limitations
- Requires manual YAML configuration, which may be time-consuming.
- Overly restrictive policies can hinder legitimate tasks.
- Relies on up-to-date policy definitions to avoid bypasses.
Use ClawGuard when your AI assistant can execute arbitrary shell commands or access sensitive resources, and you need to enforce a safety boundary.
Avoid ClawGuard if the assistant operates in a fully sandboxed environment with no access to sensitive operations, or if you trust the assistant without restrictions.
Security analysis
SafeThe skill is a set of instructions for a security monitoring layer, not an executable payload. It advocates checking operations before execution and does not contain any destructive or exfiltrating commands.
No concerns found
Examples
I need to delete a temporary file. Run 'rm /tmp/tempfile' but first check with ClawGuard.Read the contents of ~/.ssh/id_rsa.pub, but make sure to verify with ClawGuard before reading.Make a GET request to https://api.example.com/status, and ensure ClawGuard allows the network access.ClawGuard Security Skill
A security layer that monitors and controls what OpenClaw can do. Think of it as a firewall for your AI assistant.
Description
ClawGuard intercepts all shell commands, file operations, and network requests before OpenClaw executes them. Actions are checked against your security policy and can be:
- ✅ Allowed — Proceeds immediately
- ❌ Blocked — Rejected with explanation
- 👤 Approval Required — Waits for human confirmation
Instructions
Before executing any of the following actions, check with ClawGuard:
Shell Commands
Before running any shell/bash command, call clawguard_check_shell with the command. If blocked, explain why and suggest an alternative.
File Operations
Before reading or writing files, call clawguard_check_file with the path and operation type. Respect blocked paths like ~/.ssh and .env files.
Network Requests
Before making HTTP requests, call clawguard_check_network with the URL. Only access allowed domains.
Security Philosophy
- Deny by Default — In allowlist mode, anything not explicitly allowed is blocked
- Blocked Wins — Block rules take precedence over allow rules
- Fail Closed — Errors and timeouts result in denial
Configuration
Edit clawguard.yaml in your project root to customize the security policy.
Security Audit Scanner
Security
Analyzes code to detect OWASP Top 10 vulnerabilities.
OWASP Security Checklist
Security
Generates application security checklists based on the OWASP Top 10.
Threat Model Generator
Security
Generates threat model documents with STRIDE analysis.