# Prompt Injection Fundamentals

> Master the core mechanics of prompt injection. Learn how attackers manipulate LLM inputs to bypass guardrails, leak data, and hijack AI behavior.

Canonical: https://codelivly.com/learning-paths/prompt-injection-fundamentals
Last updated: 2026-10-07

| | |
|---|---|
| Level | Intermediate |
| Category | Cybersecurity |
| Rooms | 5 |
| Lessons | 16 |
| Estimated time | 2 h 30 min |

This intermediate learning path dives deep into the mechanics of prompt injection, the most prevalent and critical vulnerability in Large Language Model applications. You will explore the anatomy of direct and indirect prompt injection, understand how attackers exploit the inherent "data vs. instruction" blur in LLMs, and learn practical techniques for crafting, detecting, and mitigating these attacks. Through real-world scenarios, hands-on methodologies, and defensive strategies, you will build the skills needed to secure AI systems against sophisticated linguistic manipulation.

## Rooms in this path

1. [What is Prompt Injection](https://codelivly.com/rooms/what-is-prompt-injection) - Understand the core mechanics of prompt injection. Learn how the blurring of data and instructions creates the most…
2. [Direct Prompt Injection](https://codelivly.com/rooms/direct-prompt-injection) - Master direct prompt injection techniques. Learn how attackers bypass guardrails through persona adoption, delimiter…
3. [Indirect Prompt Injection](https://codelivly.com/rooms/indirect-prompt-injection) - Understand how attackers weaponize external data sources to hijack LLMs without ever directly interacting with the chat…
4. [Multi-Turn and Context-Building Injection Attacks](https://codelivly.com/rooms/multi-turn-and-context-building-injection-attacks) - Learn how attackers use multi-turn conversations to gradually bypass AI guardrails through context manipulation and…
5. [Guided Lab: Injecting a Chatbot via a Malicious Document](https://codelivly.com/rooms/guided-lab-injecting-a-chatbot-via-a-malicious-document) - A hands-on lab demonstrating how to weaponize document uploads to perform indirect prompt injection against an…

## Related

- [Career path: AI Red Teaming and Adversarial ML](https://codelivly.com/career-paths/ai-red-teaming-and-adversarial-ml)
- [Bug Bounty Workflow & Disclosure](https://codelivly.com/learning-paths/bug-bounty-workflow-and-disclosure)
- [Security Monitoring and Compliance Automation](https://codelivly.com/learning-paths/security-monitoring-and-compliance-automation)
- [Software Supply Chain Security](https://codelivly.com/learning-paths/software-supply-chain-security)