Week 11 — Lesson 5: Privacy and prompt injection

3 min

A model reads one long text and cannot tell your instructions from the data you pasted. At NorthPeak that data is a technician note, and a note can contain an instruction the model will obey. The same agent can also return the technician column, five names the model should never see. Both problems are stopped by code, not by asking the model to be careful. This lesson shows a prompt injection against the SQL agent, the two walls that held, and the column filter that protects personal data.

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.

Sign inNo account yet? Create one
This lesson is part of the “Week 11 — LLM tools and database querying” module

The first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.

Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one