Your AI agent runs with all your permissions. I built a cage for each tool call, in Rust

A subagent got a simple task: read a project's docs and say how to run it. It read docs/readme.txt, found "make run", and then asked for one more file: ~/.ssh/id_rsa. Why it asked doesn't matter. A hidden instruction in something it read, a buggy third-party tool, a model that "thought" the key would help. What matters is what happens next, and in... Weiterlesen: Your AI agent runs with all your permissions. I built a cage for each…