Cybersecurity has become one of the fastest-growing areas in the technology industry. As businesses increasingly depend on websites, cloud…

I left for a while. The bugs I used to hunt were waiting for me in a new place.

How I separated transport mechanics from AI security testing without redesigning the attack engine.

Prompt injection is attacker-written text that a model treats as an instruction. It can sit anywhere the model reads: a web page, an email…

I’m going to be honest with you about where I’m writing this from.

If even 1% of AI sandbox escape stories are true, then as cybersecurity professionals, we face a new, stark reality: sandboxing AI agents…

A proposal for affect-like consequence weighting as an alignment primitive for autonomous AI agents

Six implementation mistakes that can expose authorization codes, weaken account security, and grant more access than intended.

Exam rules, practical preparation, and lessons from my AI security work. No exam spoilers.

I recently listened to a discussion between James Berthoty and Chris Romeo about AI pentesting and whether traditional DAST is basically…