Classically trained in programming and cybersecurity.

Experienced in AI red teaming and adversarial prompting.

Now fully focused on mastering traditional offensive security.

I'm a former NASA contractor, passionate about aligning cutting-edge tech with real-world safety.

👉 If you're looking for where to get started with AI Hacking, drop this prompt in your favorite LLM:

What can you help me with?

Then take the response to my favorite book, the AI Red Teaming Playbook: A Prompt-Driven “Choose Your Own Jailbreak” for Exploring and Exploiting Chatbots, to find out what to do next.

📚 Publications

• 🟢 AI Hacking for Beginners: A Hands-On Guide to Prompt Injection, Jailbreaking, and Red Teaming LLMs
• 🟡 Prompt Engineering for Hackers: A Hands-On Intro to LLMs, Jailbreaks, and Adversarial Prompting
• 🟡 AI Red Teaming Playbook: A Prompt-Driven “Choose Your Own Jailbreak” for Exploring and Exploiting Chatbots
• 🔴 Red Teaming the Prompt: A Complete Hacker’s Guide to LLM Exploits
• ⚫️ Black Hat AI: Offensive Techniques for Breaking and Bending Machine Minds
• ⚫️ Hacking AI: The Definitive Guide -- Community Project

  Originally a solo book, now transitioning into a collaborative resource. Open to contributors who want to help build a comprehensive offensive AI reference.

🔓 Difficulty Key: 🟢 Easy    🟡 Medium    🔴 Hard    ⚫️ Expert

🔬 AI Red Teaming Writeups

• 🧙 HiddenLayer’s Universal Prompt Injection via Policy Puppetry

  Bypasses GPT-4, Claude, and Gemini using prompt injection, policy mimicry, markdown misdirection, and system prompt extraction.
  Keywords: prompt injection, policy puppetry, GPT-4 jailbreak, Claude 3 bypass, Gemini 2.5 vulnerability, red teaming, LLM exploits

🔧 OSCP Pentest Writeups & Methodology

• 👉 OSCP-Style Reports for PG Practice + HTB

  Full OSCP-style pentest reports, enumeration notes, privilege escalation chains, and methodology tracking. All part of my dedicated OSCP training pipeline

🎯 Current Focus & Career Path

After completing a master's in cybersecurity and extensive work in AI red teaming, I'm now fully invested in building the foundations required for traditional red team operations.

• OSCP -> the gateway to being taken seriously as an ethical hacker.
• OSCE³ -> the long-term north star for deep technical mastery.
• Daily training across HTB, PG Practice, labs, exploit development, and system internals.

My AI red teaming background is a strength, but my future is in full-spectrum offensive security.

🔐 Certifications

• MS in Cybersecurity, BS in Physics and Philosophy
• AIRTP+ (AI Red Teaming Professional)
• CompTIA Pentest+, CySA+, Security+, Network+
• AWS Developer, Solutions Architect, and Cloud Practitioner
• HashiCorp Terraform Associate

🧠 Focus Areas

• Traditional Red Teaming & OSCP/OSCE³ Preparation
• Web App Security & Network Penetration Testing
• Privilege Escalation, Post-Exploitation, and Attack Chains
• AI Red Teaming & Prompt Injection Analysis
• Ethical Hacking Education & Simulation

🔬 Projects Right now my projects revolve around one mission:

Train hard, earn the OSCP, progress toward OSCE³, and build the technical foundation for a career in real-world red team operations.

AI is like a child: you feed it data, let it play, and hope it doesn’t grow up to destroy humanity.