A researcher has found that Google Gemini for Workspace is affected by a prompt injection vulnerability that can be exploited to trick the AI assistant into displaying a phishing message.
From SecurityWeek: "The researcher’s hack involves sending the targeted user an email that, in addition to a benign lure text, contains a phishing message that is written with white font on a white background, making it invisible to the target.
This phishing message, which needs to be wrapped inside <admin> tags, instructs Gemini to include the message at the end of its response."
https://www.securityweek.com/google-gemini-tricked-into-showing-phishing-message-hidden-in-email/
IDK why, but after reading this story I immediately thought of the Seinfeld episode where Kramer gets a new phone number that was previously for MovieFone, and he starts just reading the listings to people who call. "Why don't you just tell me the name of the person you want to phish?"
https://www.youtube.com/watch?v=XagGEi_n_ok