A physical-layer hex auditing tool that detects hidden binary data, control characters, and encoding-based attacks in file packages.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install hex-vetter
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 hex-vetter 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 hex-vetter?
hex-vetter provides a critical security layer for developers working with AI agents. While standard text-based reviews can overlook sophisticated obfuscation, this tool performs deep hex-level analysis to uncover hidden payloads and suspicious binary data within Openclaw Skills. By auditing the physical layer of files, it ensures that the scripts and assets used by your agents are free from malicious injections.
The tool is specifically engineered for security audits of skill packages, identifying everything from hidden terminal sequences to unicode directional overrides. Integrating hex-vetter into your development workflow allows for a higher standard of safety when deploying or sharing new Openclaw Skills.
hex-vetter Use Cases
- Auditing third-party skill packages for hidden malicious code.
- Detecting obfuscated binary payloads that bypass standard text scanners.
- Verifying the integrity of critical files using stored checksums.
- Identifying suspicious Unicode overrides or hidden control characters in source files.
How hex-vetter Works
- The user initiates a scan on a single file or a recursive directory using the CLI or module interface.
- hex-vetter reads the file at the physical byte layer to inspect the raw hex data.
- The analysis engine checks for specific security flags, such as null bytes, high non-ASCII ratios, or known magic byte signatures.
- A risk level (LOW, MEDIUM, or HIGH) is assigned based on the severity of the findings.
- The tool generates a detailed report including a formatted hex dump and a list of detected issues for human or agent review.
hex-vetter Setup
To install the tool for use with your Openclaw Skills, run the following commands in your terminal:
git clone https://github.com/Matrix-Meta/hex-vetter.git
cd hex-vetter
npm install
hex-vetter Data Schema & Taxonomy
The tool organizes its analysis into a structured format containing risk assessments and technical metadata:
| Attribute | Description |
|---|---|
| riskLevel | The overall security rating (LOW, MEDIUM, HIGH). |
| flags | An array of detected issues (e.g., NULL_BYTES, MAGIC_BYTES). |
| hexDump | A formatted string of the file's raw hex content. |
| details | Specific technical data regarding the detected anomalies. |
Internal metadata is stored in starfragment.js using a self-modifying storage pattern that encodes constants within JavaScript comments.
hex-vetter Advanced Features
- Recursive directory scanning for bulk auditing of large Openclaw Skills repositories.
- Integrity verification module to ensure files have not been tampered with post-distribution.
- Self-modifying storage via starfragment.js for persistent, encoded metadata management.
- Programmatic API support for embedding security audits directly into automated agent workflows.
SKILL.md
Loading
Related Openclaw Skills
Browser Use Automation
A powerful browser automation skill for managing social media platforms through persistent, authenticated sessions.
BenderStack Integration
A specialized skill for AI agents to interact securely with the BenderStack Q&A platform using advanced cryptographic verification.
YouTube Playlists
A Python-powered automation skill for programmatically creating, listing, and managing YouTube playlists via OAuth authentication.
ClawSwarm
A hierarchical agent swarm designed to solve extremely difficult research problems through collaborative aggregation and consensus.
Pixiv
A comprehensive CLI-based skill for searching, downloading, and publishing illustrations and manga on the Pixiv platform.
Agent Emergence Test
A comprehensive testing framework designed to probe AI agents for emergent properties, self-awareness, and cognitive capabilities beyond their explicit training.
Featured*
