MacMusic  |  PcMusic  |  440 Software  |  440 Forums  |  440TV  |  Zicos
disguising
Recherche

Researchers exploit OpenAI's Atlas by disguising prompts as URLs

lundi 27 octobre 2025, 14:54 , par TheRegister
NeuralTrust shows how agentic browser can interpret bogus links as trusted user commands
Researchers have found more attack vectors for OpenAI's new Atlas web browser – this time by disguising a potentially malicious prompt as an apparently harmless URL.…
https://go.theregister.com/feed/www.theregister.com/2025/10/27/openai_atlas_prompt_injection/

Voir aussi

News copyright owned by their original publishers | Copyright © 2004 - 2025 Zicos / 440Network
Date Actuelle
lun. 27 oct. - 19:02 CET