Limit it, don't inhibit it
A practical way to apply least privilege to a coding agent: a few hard walls, and plenty of room to move inside them.
// tag
#security
2 posts
I told the AI to escalate its own privileges. It refused.
Mid-task, my agent hit a permission it didn't have. I told it to grant itself the capability. It couldn't — and I've come round to thinking that's exactly right. Part 4 of a series.