I'd stay clear of AI browsers. Researchers found it vulnerable to "indirect prompt injection" attacks via hidden content or screenshots, letting hackers siphon your logged-in data without you knowing. Some tests even showed it getting tricked into bogus purchases or malware downloads.
Some great advice on using AI the right way. Thanks Kevin!
I'd stay clear of AI browsers. Researchers found it vulnerable to "indirect prompt injection" attacks via hidden content or screenshots, letting hackers siphon your logged-in data without you knowing. Some tests even showed it getting tricked into bogus purchases or malware downloads.
Thanks for the heads up! Will do some reading on this. have any links I could go to?
https://brave.com/blog/unseeable-prompt-injections/
https://techcrunch.com/2025/10/25/the-glaring-security-risks-with-ai-browser-agents/
https://www.nbcnews.com/tech/tech-news/ai-browsers-comet-openai-hacked-atlas-chatgpt-rcna235980
https://layerxsecurity.com/blog/cometjacking-how-one-click-can-turn-perplexitys-comet-ai-browser-against-you/
Thanks!