Manage risk, don’t avoid it. – Gwynne Shotwell, President and COO of SpaceX
I'm an AI Security Engineer focused on how AI systems get attacked and how to defend them.
AI is moving faster than the security around it, and most of what’s out there is theory. I learn best by doing, so I build hands-on labs. First I break AI on purpose: prompt injection, poisoned tools, hijacked agents. Then I build the defenses and attack those too, to see where they hold and where they break. You run everything yourself and see how it actually works.
Everything here comes with real code you can run, fork, and adapt. Have ideas, found a better attack, or want to help? Reach out 🤝
A small Python service for Google SecOps that watches every feed, runs three independent checks per feed, restarts what it can, files one Jira ticket per outage with a Gemini summary, and emails the owner. No agent framework. No MCP. Just a YAML config and a Cloud Run Job. Open source, v1, contributions welcome.
A real-world POC: I gave Claude access to Elastic SIEM, Jira, Confluence, and Gmail — and let it triage a broken log feed autonomously. Here's exactly what happened, and how to set it up yourself.
Build your first autonomous AI agent with CrewAI — deployable Python code, multi-agent systems, and real API integrations for security engineers.
A practical field guide to prompting for security engineers — use structure, context, and examples to get consistent, high-quality results from LLMs.
