"a prompt-injection vulnerability in Google Gemini for Workspace that allows a threat-actor to hide malicious instructions inside an email. When the recipient clicks “Summarize this email”, Gemini faithfully obeys the hidden prompt and appends a phishing warning that looks as if it came from Google itself."
https://0din.ai/blog/phishing-for-gemini So simple: a white-on-white hidden prompt (or in 0px font), and the mega geniuses who push compulsory "A.I." on us didn't think of it. FFS.