← Back to home

Blog

Notes on AI-powered pentesting, custom security tooling, and securing AI systems.

August 2, 2026pentestingaiprocess

Running a pentest in 3 days with custom AI tools

The workflow behind 3-day pentests: where my custom tooling saves hours, and where a human still makes every call.

Read more →
July 30, 2026ai-securityprompt-injectionllm

The #1 security mistake I see in AI systems

Missing input validation between the user and the model is the most common and most dangerous gap. How to close it.

Read more →
July 25, 2026pentestingai-securitycoverage

Most pentests miss AI vulnerabilities. I test both.

Traditional pentesting and AI-system security are different disciplines. Shipping an AI product means you need both.

Read more →