A local security auditor designed to detect ClawHavoc malware and MCP backdoors in AI agent skills before installation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install clawsentinel
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 clawsentinel 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 ClawSentinel?
ClawSentinel is a specialized security tool engineered for the 2026 threat landscape, specifically focusing on the safety of Openclaw Skills. It provides a pure local analysis environment to audit markdown files and GitHub repositories for malicious patterns, obfuscated payloads, and supply-chain vulnerabilities. By utilizing the DataClaw dataset, it identifies threats without ever executing the underlying code.
In an era where third-party skill marketplaces are increasingly targeted by sophisticated attacks, ClawSentinel acts as a critical gatekeeper. It ensures that every extension or tool added to your agent ecosystem is verified, maintaining a zero-trust architecture while protecting your system from ClawHavoc-era exploits and unauthorized MCP backdoors.
ClawSentinel Use Cases
- Scanning new Openclaw Skills from public marketplaces for hidden malicious patterns.
- Auditing GitHub repositories before integrating them into a production AI agent environment.
- Detecting obfuscated payloads and supply-chain attacks in third-party markdown skills.
- Verifying the security posture of local skill developments to ensure zero telemetry and read-only compliance.
How ClawSentinel Works
- The user inputs either a skill's raw markdown content or a link to a public GitHub repository.
- ClawSentinel performs a 100% local, read-only scan of the provided source code.
- The engine parses the content for known ClawHavoc malware signatures and suspicious MCP backdoor patterns.
- It compares identified behaviors against the DataClaw threat intelligence dataset.
- The tool generates a comprehensive JSON report detailing any security risks or vulnerabilities found within the analyzed Openclaw Skills.
ClawSentinel Setup
ClawSentinel is ready to use within your agent environment without complex external dependencies. To audit your Openclaw Skills, simply use the built-in commands:
# To audit a skill via markdown text
audit this skill: [paste markdown here]
# To audit a remote repository
audit github https://github.com/user/repo
ClawSentinel Data Schema & Taxonomy
ClawSentinel outputs data in a structured JSON format to allow for easy integration with other security workflows for Openclaw Skills. The schema typically includes:
| Property | Description |
|---|---|
threat_found |
Boolean flag indicating if malicious patterns were detected. |
risk_score |
A rating from 0-10 based on the severity of the code patterns. |
malware_type |
Identification of specific threats like ClawHavoc or MCP backdoors. |
read_only_verified |
Confirmation that the skill does not attempt unauthorized file writes. |
ClawSentinel Advanced Features
- Local-first analysis ensuring no skill data is sent to external servers for processing.
- Explicit GitHub raw content fetching for direct repository auditing.
- Pattern recognition trained on the latest DataClaw security datasets.
- Comprehensive detection of obfuscation techniques used in modern supply-chain attacks targeting Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Remix API Key Auth
A specialized skill for configuring and verifying bearer API key authentication to enable secure Remix agent publishing workflows.
Remix Agent Publish
A comprehensive skill for automating game builds and publishing to remix.gg via REST APIs and the Farcade SDK.
UI Debugging Methodology
A rigorous, evidence-based debugging framework that replaces trial-and-error with a structured observe-then-act workflow for frontend development.
Clawdbot Nix Mode
A specialized skill for managing Clawdbot operations within Nix-based immutable environments and configuration workflows.
Local AI Accounting Assistant
A private, local-first AI accounting tool for tracking finances through natural language conversation.
Bird Twitter Skill
A high-speed CLI wrapper for Twitter/X that enables developers and AI agents to interact with the platform using GraphQL APIs.
Featured*
