I build an open-source runtime security layer for AI agents – Let's break it

A developer has created an open-source runtime security layer for AI agents and is seeking feedback. The project is hosted on GitHub and a discussion thread is available on Hacker News. The project has garnered some interest, with 2 points and a comments section, although no comments have been made yet. The developer is inviting others to review and break the project. The goal of the project is to provide a security layer for AI agents.