Design Patterns for Securing LLM Agents against Prompt Injections

Abstract

As AI agents, powered by Large Language Models (LLMs), become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent’s reliance on natural language inputs, an especially dangerous threat when agents are granted tool access or handle sensitive information. In this work, we propose a set of principled design patterns for building AI agents with provable resistance to prompt injection. We systematically analyze these patterns, discuss their trade-offs in terms of utility and security, and illustrate their real-world applicability through a series of case studies.

David Froelicher

Research Manager

My research interests include applied cryptography, AI, distributed systems and genomic privacy.