There is a paper that reframes prompt injection in a way that is hard to unsee: Prompt Injection as...
Prompt injection is role confusion, and your MCP gateway can't see it
Related
Building a 10-Agent Security Civilization with Qwen and Alibaba Cloud 🛡️🤖
Security auditing is broken. If you’ve ever run a static analysis tool (SAST) on a large codebase,...
I Packed DeepSeek V4 + Claude Code Into a Starter Kit. Clone It and Ship.
TL;DR: I spent weeks tuning DeepSeek V4 to feel native inside Claude Code. The result: a one-command...
My repository isn't written for humans — I run my whole life with Claude Code
I run my life as one Git repo operated by Claude Code agents: journaling, self-analysis, investing, parenting. The primary reader isn't me; it's the AI. Here's the whole map.