Navigation
Recherche
|
OpenAI's Atlas shrugs off security concerns over prompt injection
jeudi 23 octobre 2025, 01:49 , par TheRegister
'Trust no AI' says one researcher
OpenAI's brand new Atlas browser is more than willing to follow commands maliciously embedded in a web page, an attack type known as indirect prompt injection.…
https://go.theregister.com/feed/www.theregister.com/2025/10/22/openai_defends_atlas_as_prompt/
Voir aussi |
56 sources (32 en français)
Date Actuelle
jeu. 23 oct. - 06:11 CEST
|