A Multi-Layer Security Framework for Prompt Injection and Knowledge Poisoning Mitigation in Agentic Retrieval-Augmented Generation Systems
Year: 2026
Type: preprint
Abstract: Retrieval-Augmented Generation (RAG) improves the factual usefulness of Large Language Models (LLMs) by grounding generation in external knowledge. When RAG is combined with autonomous agents, the system can plan multi-step tasks, retrieve information, and invoke external tools, but the additional autonomy also creates new attack surfaces. This paper proposes a Multi-Layer Security Framework (MLSF) for agentic RAG systems that combines input inspection, retrieved-context security, provenance verification, tool authorization, and output verification. The framework is designed around a practical Python technology stack consisting of LangChain, LangGraph, Mistral Small, embeddings, ChromaDB, FastAPI, and Docker. A controlled evaluation environment is defined with five attack categories: direct prompt injection, indirect prompt injection, knowledge poisoning, tool misuse, and context manipulation.
Author: Mehra, Rohan
Institution: Karachi Institute of Economics and Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7210295494
Cites:
Cited by:
Related to: