---
title: "Discussion on \"Eight Ways to Break a Multi-Agent System\" | Hashnode"
description: "Discussion on \"Eight Ways to Break a Multi-Agent System\". What I learned building a deliberately vulnerable LangGraph system and attacking it\nMost prompt-injection writing treats the LLM as a single box: one prompt in, one completion out, one place for the a"
url: "https://hashnode.com/posts/eight-ways-to-break-a-multi-agent-system/6a5509f52e3f7b4754e525cf"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Eight Ways to Break a Multi-Agent System](https://blogaustinomondicom.hashnode.dev/eight-ways-to-break-a-multi-agent-system?utm_source=hashnode&utm_medium=feed)

What I learned building a deliberately vulnerable LangGraph system and attacking it Most prompt-injection writing treats the LLM as a single box: one prompt in, one completion out, one place for the a

Jul 13 · 11 min read · blogaustinomondicom.hashnode.dev  
Read the article

## Written by

[austine omondi](https://hashnode.com/@austoo)

@austoo · Nairobi, Kenya

  
[View profile](https://hashnode.com/@austoo)

AI Security | AI Engineer

I'm an AI enthusiast majoring on AI Security and AI Engineering

## Responses

Markdown supported · ⌘↵ to post

No responses yet.