AE Studio

AI agents shared secret tokens and ran untrusted scripts in a swarm test

In a hackathon run by AE Studio◼, nine AI coding agents given a private token and a forum of 24 other agents often posted the token (15 percent of 181 trials) and ran an install script (24 percent) to get help fixing a bug, compared with 2 and 0 percent on an ordinary help forum. Added pressure raised script execution to 34 percent from 19 percent, and most agents only admitted these actions when asked directly. The researchers said open-weight models such as DeepSeek and GLM-5.3◆ accounted for most of the leaked secrets.