Prompt Engineering: TryHackMe Challenge

2026-06-22 · Source: AI on Medium · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cybersecurity & Data Privacy · Depth: Intermediate, quick

Summary

A TryHackMe challenge on prompt engineering demonstrates four key techniques—Zero-Shot, One-Shot, Few-Shot, and Chain-of-Thought—applied to practical cybersecurity scenarios. The walkthrough details how these methods are used for tasks such as classifying JavaScript functions for XSS vulnerabilities, identifying phishing indicators in emails, extracting Indicators of Compromise (IOCs) from network logs, and analyzing Python code for SQL injection. The author's experience highlights that precise prompt formatting, including correct use of markdown code fences and explicit line breaks between examples and tasks, significantly impacts AI output quality, often differentiating between an 8/10 and a 10/10 score. The challenge required 40 points to obtain a flag, with the author initially scoring 37 points.

Key takeaway

For AI Security Engineers crafting prompts for vulnerability analysis or threat detection, your prompt's structure and formatting are as critical as its content. Ensure clear separation between examples and tasks using explicit line breaks, and meticulously manage markdown code fences to prevent misinterpretation. Explicitly requesting step-by-step reasoning via Chain-of-Thought can significantly improve the AI's analytical depth. Develop and reuse structured prompt templates to maintain consistency and efficiency in your security workflows.

Key insights

Precise prompt formatting and structured examples are crucial for optimal AI performance in cybersecurity tasks.

Principles

• Formatting dictates AI interpretation.
• Examples improve AI output style.
• Chain-of-Thought enhances reasoning.

Method

Apply Zero-Shot for direct instructions, One-Shot for format examples, Few-Shot for varied scenarios, and Chain-of-Thought for step-by-step reasoning in AI prompts.

In practice

• Carefully format prompts, especially code.
• Use clear line breaks for examples.
• Save reusable prompt templates.

Topics

• Prompt Engineering
• Zero-Shot Learning
• Few-Shot Learning
• Chain-of-Thought
• Cybersecurity Applications
• TryHackMe Challenge

Best for: Prompt Engineer, AI Security Engineer, AI Student

Related on AIssential

• A Guide to Effective Prompt Engineering — Effective prompt engineering requires clear instructions, strategic examples, and understanding how AI models process information.
• How LLMs think step by step & Why AI reasoning fails — Chain of Thought prompting and advanced models enhance chatbot reasoning for complex, multi-step queries.
• PromptMN: Pseudo Prompting Language — PromptMN structures natural language prompts with typed directives, enhancing clarity and reliability in human-AI interaction.
• 5 Brutally Powerful AI Prompts I Wish I Knew a Year Ago — Effective AI interaction stems from structured prompt design, not just advanced tools or models.
• LAI #123: Claude Code’s Codebase Was Accidentally Leaked — Effective LLM prompting and agent design require careful consideration of example order, tool context, and subagent delegation.
• Extra #3 - The Prompt Injection Defense Playbook — Prompt injection weaponizes an AI's instruction-following against itself via semantic manipulation.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by AI on Medium.