https://anishbista.org/tags/security/Recent content in Security on Anish BistaHugoen-usSun, 11 Oct 2026 00:00:00 +0000https://anishbista.org/blog/sandboxing-ai-agents/Sun, 11 Oct 2026 00:00:00 +0000https://anishbista.org/blog/sandboxing-ai-agents/<p>Most of us have now run an AI agent that writes code and then runs it. Many of us did that on a laptop with cloud credentials in <code>~/.aws</code>, an API token in the environment, and SSH keys in <code>~/.ssh</code>.</p> <p>My argument in this post is simple: <strong>an AI agent is a program whose exact actions you don’t write and can’t fully predict. You set the goal and the tools, and anything it reads can try to steer it. Treat it like untrusted code and put it in a box.</strong></p>