I Asked My Coding Agent a Yes-or-No Question. It Made a Commit.
I asked my AI coding agent a yes-or-no question. It made a commit instead. I never asked it to change anything. When did "can do" become "authorized to do"? This incident changed how I think about AI agent security. Here's what happened →
We haven't written up this one. Dev.to has the full story — the link below goes straight to it.