# Direct Prompt Injection

> Master direct prompt injection techniques. Learn how attackers bypass guardrails through persona adoption, delimiter escaping, and linguistic obfuscation.

Canonical: https://codelivly.com/rooms/direct-prompt-injection
Last updated: 2026-10-07

| | |
|---|---|
| Level | Intermediate |
| Category | Cybersecurity |
| Lessons | 4 |
| Estimated time | 30 min |
| XP | 100 |

This module dives deep into direct prompt injection, where attackers interact directly with the LLM to hijack its behavior. You will explore common attack vectors like persona adoption, delimiter escaping, multi-turn manipulation, and linguistic obfuscation. Through practical examples and defensive strategies, you will learn how to identify, exploit, and mitigate these direct linguistic attacks in real-world AI applications.

## Lessons

1. What is Direct Prompt Injection (30 min)
2. Basic Instruction Override Techniques (30 min)
3. Role-Confusion and Delimiter Injection Techniques (30 min)
4. Guided Lab: Direct Injection Against a Test Chatbot (30 min)

## Related

- [Learning path: Prompt Injection Fundamentals](https://codelivly.com/learning-paths/prompt-injection-fundamentals)
- [All rooms](https://codelivly.com/rooms)