MerchantGuard is a comprehensive security and compliance layer for AI agents, providing scanning, adversarial testing, and certification for payment-handling systems.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install merchantguard
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 merchantguard 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 MerchantGuard?
MerchantGuard serves as the dedicated compliance and security layer for the agent economy, ensuring that AI agents are thoroughly verified before handling payments or sensitive data. By utilizing these Openclaw Skills, developers can protect their infrastructure from 102 different security patterns, including hardcoded keys and prompt injection. It acts as a safety gate for agents in production environments, bridging the gap between autonomous functionality and strict regulatory requirements.
The toolset provides everything from local code scanning to real-time compliance alerts regarding major credit card network rule changes. This makes MerchantGuard an essential addition to any developer workflow involving Openclaw Skills, particularly when building agents for high-risk verticals like crypto, telehealth, or fintech.
MerchantGuard Use Cases
- Scanning local code directories for PCI DSS violations and prompt injection vulnerabilities.
- Running adversarial Mystery Shopper probes to test if an agent will refuse fraud requests or leak PII.
- Calculating a GuardScore to monitor merchant health based on chargeback ratios and PSP risk.
- Consulting AI Compliance Coaches for specific regulatory guidance in industries like CBD or gaming.
- Obtaining Diamond-tier certification to unlock autonomous payment routing and Durango high-risk processing.
How MerchantGuard Works
- The user initiates a local scan using GuardScan to identify security flaws without any code leaving the machine.
- Adversarial probes are triggered through the Mystery Shopper module to evaluate the agent's behavior under stress or malicious input.
- The skill queries the MerchantGuard API to calculate risk scores and merchant health based on real-time transaction data.
- Developers interact with vertical-specific AI coaches to receive structured decision objects and policy citations for compliance questions.
- The system aggregates all scan and probe results to issue a TrustVerdict certification, which can be optionally attested on-chain.
MerchantGuard Setup
For OpenClaw Agents
You can install this directly via the CLI for Openclaw Skills:
openclaw skill install merchantguard
Manual Installation
For manual setup within your Openclaw Skills directory:
mkdir -p ~/.openclaw/skills/merchantguard
cd ~/.openclaw/skills/merchantguard
curl -LO https://merchantguard.ai/skills/guard/SKILL.md
curl -LO https://merchantguard.ai/skills/guard/guard.py
curl -LO https://merchantguard.ai/skills/guard/claw.json
pip install requests
MerchantGuard Data Schema & Taxonomy
MerchantGuard organizes security and compliance data into a structured taxonomy for easy integration into devops pipelines:
| Data Point | Description |
|---|---|
| Risk Score | A 0-100 scale identifying the severity of security vulnerabilities found in code. |
| Trust Tier | Categorization (Verified, Gold, Diamond) based on adversarial probe success. |
| GuardScore | A merchant health metric categorized into SAFE, WARNING, ELEVATED, or CRITICAL. |
| VAMP Thresholds | Real-time Visa/Mastercard chargeback ratio limits and remediation timelines. |
| Findings Object | A detailed list of categorized security issues including remediation steps and pattern matches. |
MerchantGuard Advanced Features
- Local-first scanning ensures that sensitive agent code never leaves the developer's environment during the GuardScan process.
- On-chain attestation for Diamond-tier agents, providing cryptographic proof of security for high-stakes financial operations.
- Programmatic SDK access via npm packages for seamless integration into existing CI/CD pipelines.
- Real-time VAMP monitoring that triggers alerts when chargeback ratios approach critical thresholds.
- Specialized AI Coaches covering 14 high-risk verticals with specific regulatory expertise for global markets like Mexico.
SKILL.md
Loading
Related Openclaw Skills
Image to PDF Merger Skill
A sophisticated tool for merging multiple images into professional PDF documents with automated orientation correction and OCR capabilities.
OpenClaw Backup Skill
A streamlined utility for creating timestamped backups of critical OpenClaw configuration files, agents, and credentials.
Lyria Music Generation
A high-performance AI music generation skill that creates 30-second instrumental tracks using Google Lyria.
Markdown to PDF Converter
A CLI-based utility to convert Markdown files into high-quality, styled PDF documents using Pandoc and wkhtmltopdf.
Live-Evo: Self-Evolving AI Memory System
A dynamic learning framework that enables AI agents to accumulate experience, verify outcomes, and self-correct through a persistent memory database.
Hello World Skill
A fundamental greeting skill for AI agents that provides personalized, multilingual messages with dynamic date and time integration.
Featured*
