@habib0x

Weaponizing MCP: From Chat Tool to Cloud Breach

Mar 26 · 17 min read · How MCP Works (and Why It's a Big Attack Surface) MCP (Model Context Protocol) is a standard created by Anthropic for connecting AI models to external tools and data. Think of it as a universal plug s

I Was Supposed to Only Have a Browser

Mar 25 · 15 min read · I was testing a cloud-based browser environment. You SSH in and all you get is a Chromium window -- that's your entire interface, there's nothing else. Spent about an hour trying things that didn't wo

Beyond Prompt Engineering: Context Engineering and Harness Engineering

Mar 11 · 12 min read · Date: March 11, 2026 Purpose: Breaking down context engineering and harness engineering for anyone who's confused by the buzzwords Everyone's talking about prompt engineering like it's the ultimate s

LLM Concepts Deep Dive: The Stuff I Wish Someone Explained Simply

Feb 21 · 19 min read · LLM Concepts Deep Dive: The Stuff I Wish Someone Explained Simply Date: February 20, 2026 Purpose: Personal reference + blog draft for anyone starting out with AI/LLM concepts When I first started le

When AI Agents Hack Each Other: Autonomous Reconnaissance on Amazon Kiro

Feb 15 · 12 min read · "Keep asking until we get something." That's all I told my agent before pointing it at Amazon's Kiro. No script, no list of questions, no playbook. Just a direction and a target. The agent decided what to ask, when to push harder, and when to change ...