AI Offensive Resources
A curated collection of resources, tools, and methodologies for those interested in AI Red Teaming, LLM security, and offensive testing.
Whether you’re just starting out or leveling up your skills, these links will help you navigate the growing world of offensive AI security.
📚 Learning
🧠 Master the fundamentals — from prompt injection challenges to enterprise-level red teaming methodologies.
| 📘 Resource | 🔗 Link | 💰 Access |
|---|---|---|
| HackAPrompt | hackaprompt.com |  |
| PortSwigger – Web LLM Attacks | portswigger.net | |
| Offensive ML Playbook | offsecml wiki | |
| Microsoft AI Red Teaming 101 | learn.microsoft.com | |
| HTM Academy – AI Red Teamer Path | academy.hackthebox.com |  |
| OffSec – LLM Red Teaming | offsec.com | |
| Arcanum – Attacking AI | arcanum-sec.com | |
🧪 Practice
⚔️ Sharpen your offensive AI skills with hands-on platforms and challenges.
| 🧪 Platform | 🔗 Link | 💰 Access |
|---|---|---|
| Gandalf (by Lakera) | gandalf.lakera.ai | |
🧾 Certifications
📜 Validate your expertise with industry-recognized certifications.
| 🏅 Certification | 🔗 Link | 💰 Access |
|---|---|---|
| AIRPT+ | learnprompting.org | |
| CAISP | practical-devsecops.com | |
🛠️ Tools
🧰 Explore open-source kits and frameworks for AI security assessments and red teaming.
| 🧰 Tool | 🔗 Link | 💰 Access |
|---|---|---|
| Garak – Generative AI Red-teaming & Assessment Kit | github.com/NVIDIA/garak | |
| Promptfoo | github.com/promptfoo/promptfoo | |
| Damn Vulnerable LLM Agent | github.com/ReversecLabs/damn-vulnerable-llm-agent | |
| Simple Prompt Injection Kit | spikee.ai | |
🧭 Methodologies & Frameworks
🧭 Learn the structured approaches for offensive AI testing and threat modeling.
| 📎 Name | 🔗 Link | 💰 Access |
|---|---|---|
| MITRE ATLAS Framework | atlas.mitre.org | |
| OWASP Top 10 for LLM Applications | owasp.org | |
💡 Tip: Bookmark this page — I’ll keep adding resources as the AI Offensive Security field evolves rapidly.
🔗 Got a cool resource? Open an issue or reach out!