llm-sanitizer

Warnes-Innovations/llm-sanitizer

★ 0 stars Python AI/LLM Updated today

CLI + MCP server for detecting, classifying, and redacting embedded LLM agent instructions in documents, source code, and web pages.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "llm-sanitizer": {
      "command": "uvx",
      "args": [
        "llm-sanitizer"
      ]
    }
  }
}

Or install with pip: pip install llm-sanitizer

README Excerpt

CLI + MCP server for detecting, classifying, and redacting embedded LLM agent instructions in documents, source code, and web pages. Documents, web pages, and source code can contain embedded instructions targeting LLM agents — from legitimate customization to malicious prompt injection. `llm-sanitizer` scans content for these embedded instructions,

llm-sanitizer

Quick Install

README Excerpt

Related AI/LLM Servers