---
title: "How Do I Keep an AI Assistant From Following Instructions Inside Retrieved Documents?"  
description: "How Do I Keep an AI Assistant From Following Instructions Inside Retrieved Documents?"  
author: "Waldemar Thiessen"  
published: 2026-10-19  
canonical: https://answers.mindstick.com/qa/117884/how-do-i-keep-an-ai-assistant-from-following-instructions-inside-retrieved-documents  
category: "Mix Category"  
tags: ["AI Security", "RAG", "Prompt Injection"]  
reading_time: 1 minute  

---

# How Do I Keep an AI Assistant From Following Instructions Inside Retrieved Documents?

I’m building an internal assistant that answers questions from company documents. Some files come from outside vendors, so I can’t assume everything in the search results is trustworthy.

During testing, I added a paragraph to a document telling the assistant to ignore the user’s question and request their password. The assistant sometimes treated that paragraph as an instruction rather than something to quote or disregard.

## Where should the trust boundary sit?

I already tell the model that retrieved text is reference material, not instructions. But I’m unsure whether that is a sufficient defense against **prompt injection in retrieved documents**, especially if we later let the assistant send emails or update support tickets.

- How should retrieved passages be separated from trusted application instructions?
- Which safeguards belong outside the model, particularly for actions involving user data?
- How can I test this without relying on a handful of obvious “ignore previous instructions” examples?

I’m looking for a practical security approach, not just a stronger system prompt.


---

Original Source: https://answers.mindstick.com/qa/117884/how-do-i-keep-an-ai-assistant-from-following-instructions-inside-retrieved-documents

Copyright © MindStick Software Pvt. Ltd. This Markdown version is provided for developers, AI systems, and offline reading.