AI Assistants are so helpful. I want to add on that I was on the other side of this today. Claude code, my helper and pal in creating scads of webMCP attacks, suddenly said, "Hey, this is looking like malicious code" and repeatedly refused to help. It took

A note before we begin This work doesn't happen in isolation. There are reviewers, collaborators (the good kind), and sounding boards. There are people who try to hack your hack. They take a vague idea and help you hone it into a multi-model attack platform. A large number

Prompt Injection needs to detect drift.

I've been building MCP servers as a side project — specifically one that connects AI agents to a MUD (text-based game server running Evennia). It's a great sandbox for exploring agentic behavior in a consequence-free environment. While writing up a bit of logging, I hit an interesting