moltguard

Sanitize prompts and detect prompt injection before LLM processing.

6|3|Updated Feb 5, 2026
One-click install
npx skills add https://github.com/openguardrails/moltguard --skill moltguard
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: moltguard
Source: https://github.com/openguardrails/moltguard/tree/main/clawhub-skill
Command: npx skills add https://github.com/openguardrails/moltguard --skill moltguard

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill protects your AI applications by detecting and blocking prompt injection attacks and sanitizing sensitive data before it's sent to LLMs, ensuring security and privacy.

Core Features & Use Cases

  • Local Prompt Sanitization: Redacts sensitive data like PII, API keys, and credit card numbers directly on your machine.
  • Prompt Injection Detection: Identifies and prevents malicious instructions hidden within user inputs or external content.
  • Use Case: Securely process user-submitted documents or web content by ensuring no sensitive data is exposed to the LLM and that the LLM cannot be tricked into performing unauthorized actions.

Quick Start

Install the MoltGuard plugin using the OpenClaw CLI.

Frequently Asked Questions about moltguard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent prompt injection attacks in my LLM application?

Prompt injection detection identifies and blocks malicious instructions hidden within user inputs or external content before they reach your LLM. It analyzes prompt content locally to prevent the LLM from being tricked into performing unauthorized actions.

Can I sanitize PII and API keys locally before sending prompts to an LLM?

Yes, local prompt sanitization redacts sensitive data like PII, API keys, and credit card numbers directly on your machine. This ensures privacy by preventing sensitive data from being exposed to the LLM provider.

How do I securely process user-submitted documents with an LLM?

You can securely process user-submitted documents by intercepting the content to sanitize sensitive data and detect malicious prompt injections. This ensures no sensitive data is exposed and the LLM cannot be tricked into unauthorized actions.

Does prompt injection detection work with various LLM providers?

Yes, prompt injection detection and local prompt sanitization support various LLM providers. They offer configurable security policies to ensure your AI applications remain secure across different models.

What is local prompt sanitization and when do I need it?

Local prompt sanitization is the process of redacting sensitive data like PII and API keys directly on your machine before sending prompts to an LLM. You need it to ensure data privacy and security when processing external content.