High Safety Question 184 of 223

What is indirect prompt injection through retrieved documents?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

PICTURE THIS: AN LLM TURN

Text inTokens

TransformerAttention

Text outNext token

Simple meaning

An attacker poisons a wiki, email, or web page that your retriever will fetch.

WHY — Tokens instead of words?

LLMs use tokens (not full words) because it helps them:

Safety questions separate people

who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

Fixed pieces are what transformers expect as input.

STEPS — What happens step by step?

Before you speak the answer, walk the interviewer through these steps:

1
An attacker poisons a
wiki, email, or web page that your retriever will fetch.
2
Hidden instructions then run
with the privilege of your system prompt context.
3
Mitigations include treating retrieved
text as data, instruction hierarchies, and output allowlists for tools.
4
Give an example
One tiny concrete case you can say aloud.
5
Common mistake
What juniors usually get wrong.
6
Close
When you pick this over the alternative.

EXAMPLE — See it in action

Here's a short line you can speak, broken into clear beats:

Say this line

“Hidden instructions then run with the privilege of your system prompt context.”

Break into beats

Hiddeninstructionsthenrunwiththe

Speaking order

2987408337471632900

Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.

Key takeaway

An attacker poisons a wiki, email, or web page that your retriever will fetch. Hidden instructions then run with the privilege of your system prompt context.