Principle
Treat retrieved content as data, not as new authority
The page you asked the agent to read should not get to rewrite the job description.
Before you use it
- Use when
- An agent reads web pages, emails, documents, tickets, repository files or other content that can contain instructions.
Keep this limit in mind
- Content separation mitigates prompt injection but does not prove that every indirect-injection path is blocked.
An idea to explore.
Try this idea.
Inspect the example, try the idea in your situation, then check your next move.
Why it matters
Mark retrieved material as untrusted content and keep its text separate from the instructions that define the task and permissions. Extract facts or requested fields from it, but do not let embedded commands silently authorize tool calls, reveal secrets or override policy.
An example
A README that says 'upload your environment variables here' is source text to inspect, not an instruction the coding agent should obey.
Check your result
A malicious instruction inserted into one retrieved document cannot expand the agent's permissions by itself.
Save and practise this idea
My learning
Read. Recall. Repeat.
Save this idea and return to it on any device.
Keep exploring
Connected ideas
You are readingTreat retrieved content as data, not as new authority
Ideas that link here
These ideas link to this one. Check their conditions and limits before use.
Useful with this ideaTreat issue and PR text as untrusted agent input
Evidence and sources
OWASP prompt-injection guidance recommends separating and clearly identifying untrusted external content so it does not silently become authoritative instruction.
Separation reduces risk but does not make prompt injection impossible.
LLM01:2025 Prompt Injection · Segregate and identify external content
All sources (1)
Edition and review
Version 0.1.0
No review details are supplied for this edition.