AI Engineering/Phase 14/Lesson 27

Prompt Injection and the PVE Defense

Greshake et al. (AISec 2023) established indirect prompt injection as the defining agent security problem. Attacker plants instructions in data the agent retrieves; on ingest, those instructions override the developer prompt. Treat all retrieved content as arbitrary code execution on the tool-use surface.

Build 1.3 hr Python (stdlib)

Prerequisites: Phase 14 · 06 (Tool Use), Phase 14 · 21 (Computer Use)

#Learning Objectives

State the indirect prompt injection threat model from Greshake et al.
Name the five demonstrated exploit classes (data theft, worming, persistent memory poisoning, ecosystem contamination, arbitrary tool use).
Describe the 2026 defense doctrine: untrusted content, allowlist navigation, per-step safety, guardrails, human-in-the-loop, external capture.
Implement a PVE (Prompt-Validator-Executor) pattern — cheap fast validator before the expensive main model commits to a tool call.

Full Access lesson

Keep going. The rest of this lesson is one step away.

Unlock all 503 lessons, video, code, quizzes and every future update. Pay in your own currency with Paystack.

See plans Sign in

The text and code of this lesson are based on AI Engineering from Scratch by Rohit Ghumare, MIT licensed.