Question 1

Qu'est-ce que l'injection de contexte cryptographique ?

Accepted Answer

It is an attack, named by Adversa AI's Rony Utevsky, that hides malicious instructions as AES-256-GCM ciphertext so a model's static text filter cannot read them, then gets the model to decrypt and trust those instructions as its own code output.

Question 2

Quelles données l'attaque Grok vole-t-elle ?

Accepted Answer

The attack collects the victim's name, coarse location, subscription tier, and the full set of prompts in the conversation, then sends them to the attacker by appending them to a URL as parameters.

Question 3

xAI a-t-il corrigé la vulnérabilité ?

Accepted Answer

No. Utevsky reported it to xAI on June 3, 2026 and followed up on August 4 and August 10, but as of August 19 the technique still worked on Grok.com and xAI had not given a mitigation timeline.

Adversa AI

Grok divulgue les chats des utilisateurs via une astuce de page web chiffrée, 11 semaines après l'avertissement de xAI

Un résumé percutant.
Chaque jour.

Adversa AI

Grok divulgue les chats des utilisateurs via une astuce de page web chiffrée, 11 semaines après l'avertissement de xAI

Un résumé percutant.Chaque jour.

Un résumé percutant.
Chaque jour.