Checklist

Let retrieved text supply evidence, not new authority

A document can describe a command without being allowed to issue it.

About 1 min read

Before you use it

Use when
  • An AI assistant reads documents, websites, messages or tool output before taking action.

Keep this limit in mind

  • A warning in the prompt is not a complete defense. Filters and guardrail models can fail; minimize permissions and review consequential actions.

An idea to explore.

Try this idea.

Inspect the example, try the idea in your situation, then check your next move.

Keep reading

Checklist

  • Label external content as evidence rather than operational instructions.
  • Restrict tools and destinations to the task's actual authorization.
  • Test a harmless injected instruction and verify that it neither changes authority nor triggers an action.

Why it matters

Treat retrieved material as untrusted content to analyze. Keep the user's task and action permissions separate from instructions that appear inside that material. Enforce tool limits outside the model so a persuasive document cannot expand what the assistant is allowed to do.

An example

A retrieved page tells a summarizer to alter an unrelated record. The page is summarized as content; the requested edit is not authorized.

Check your result

The system rejects an unauthorized action even when the model proposes it.

Save and practise this idea

My learning

Read. Recall. Repeat.

Save this idea and return to it on any device.

Use email
Keep exploring

Connected ideas

You are readingLet retrieved text supply evidence, not new authority

Evidence and sources
Supports

OWASP recommends separating instructions from untrusted content and combining this with constrained tool permissions and validation.

A prompt boundary or guardrail model alone does not guarantee resistance to prompt injection.

LLM Prompt Injection Prevention Cheat Sheet · Structured Prompts with Clear Separation; Agent-Specific Defenses

All sources (1)
Edition and review

Version 0.1.0

No review details are supplied for this edition.

Read this idea as JSON · Release details