llamaindex-rag-security

Community

Secure LlamaIndex RAG pipelines end-to-end.

Authormaruakshay
Version1.0.0
Installs0

System Documentation

What problem does it solve?

LlamaIndex's Node is the unit of retrieval — and the unit of trust. If node metadata is lost during parsing or chunking, you lose the ability to scope retrieval, verify citations, and enforce access control. The node is the trust anchor. Guard its metadata as carefully as its content.

Core Features & Use Cases

  • Validate metadata survival across the pipeline: node.metadata should persist through parsing, chunking, retrieval, and synthesis.
  • Enforce citation integrity and scoped routing to prevent leakage or misattribution.
  • Apply data leakage prevention and access control checks within LlamaIndex storage contexts and observability paths.

Quick Start

Apply this skill to your LlamaIndex RAG stack to perform a metadata survival audit and enforce routing and citation controls.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: llamaindex-rag-security
Download link: https://github.com/maruakshay/mii-ai-security/archive/main.zip#llamaindex-rag-security

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.