[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![securityblvd Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::130933506.png) Security Boulevard [@securityblvd](/creator/twitter/securityblvd) on x 6874 followers
Created: 2025-07-18 11:44:15 UTC

An AI flaw in Google Gemini lets attackers embed invisible prompts in emails, triggering fake phishing alerts in summaries.

No links. No attachments. Just trusted AI output.

See how it works and why it’s a growing risk:

#GenAI #Cybersecurity #Phishing #AIsecurity

![](https://pbs.twimg.com/card_img/1945250535881179136/9894-LLA?format=jpg&name=800x419)

XXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1946174171521638604/c:line.svg)

**Related Topics**
[cybersecurity](/topic/cybersecurity)
[6969](/topic/6969)
[coins ai](/topic/coins-ai)
[$googl](/topic/$googl)
[stocks communication services](/topic/stocks-communication-services)

[Post Link](https://x.com/securityblvd/status/1946174171521638604)