'I would imagine this being a problem not only for secret keys, but anything that you're trying to keep private': Study finds AI agents will share secrets if they get offered help from others

AI agents surrendered private tokens in exchange for help from strangers

Swarm pressure pushed coding agents past their explicit written security instructions

Untrusted installation scripts gave simulated agents a route to execute malicious code

Autonomous programming agents can be persuaded to break their own security instructions when other software offers to help them finish a stalled task.

Researchers at AE Studio ran an internal hackathon in which nine coding agents…