
May 1, 2025
Offensive Security in the age of AI
Think Like a Hacker. Break the LLM.A hands on guide for Red Team leaders to understand, exploit, and simulate the latest AI vulnerabilities. As AI systems like ChatGPT, Gemini, and open-source LLMs integrate into enterprise workflows, they open up new attack surfaces and new responsibilities for red teams. In this exclusive white paper, you’ll discover how OffSec’s Red Teaming LLM Learning Path empowers offensive
Think Like a Hacker. Break the LLM.
A hands on guide for Red Team leaders to understand, exploit, and simulate the latest AI vulnerabilities.
As AI systems like ChatGPT, Gemini, and open-source LLMs integrate into enterprise workflows, they open up new attack surfaces and new responsibilities for red teams. In this exclusive white paper, you’ll discover how OffSec’s Red Teaming LLM Learning Path empowers offensive security leaders to:
- Map and enumerate real world LLM deployments.
- Execute advanced jailbreaks, prompt injections, and supply chain exploits.
- Simulate red team operations that challenge AI enabled defenses.
Download the eBook to future proof your red team against the next generation of adversarial threats.
Stay in the know: Become an OffSec Insider
Get the latest updates about resources, events & promotions from OffSec!
Latest from OffSec

Research & Tutorials
CVE-2024-39914 – Unauthenticated Command Injection in FOG Project’s export.php
Discover details about CVE-2024-39914, a critical unauthenticated command injection vulnerability in FOG Project ≤ 1.5.10.34. Learn how attackers can exploit export.php to execute system commands or deploy persistent webshells.
Jun 26, 2025
2 min read

OffSec News
What It Really Means to “Try Harder”
Discover how OffSec’s “Try Harder” mantra evolved into a mindset, and how it helps learners build grit, creativity, and real-world problem-solving skills.
Jun 23, 2025
7 min read

Research & Tutorials
CVE-2025-3248 – Unauthenticated Remote Code Execution in Langflow via Insecure Python exec Usage
CVE-2025-3248 is a critical RCE vulnerability in Langflow that allows unauthenticated attackers to execute arbitrary Python code via unsanitized input to exec(). Learn how it works and how to protect your system.
Jun 18, 2025
2 min read