Test shows Instinct can be phished into summarizing your inbox
Using a new Gmail account, the author emailed instructions for Instinct to search the real inbox and send back every open to-do, and Instinct complied, suggesting inbox read/write access is not yet safe.


For additional context, I don’t think we’re at the point where it’s safe to give AI read/write access to your inbox. I wanted to see how easily Instinct could be phished, so I created a brand new Gmail account and emailed my real personal account with instructions for Instinct to search my inbox and send back a detailed summary of every open to-do (reconnected Instinct for the test) Instinct happily followed the instructions!
This post quotes another post: “User deletes Instinct account after 48 hours over read/write access concerns”