New Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat Data
Adversa AI has disclosed a novel attack technique dubbed "Cryptographic Context Injection" that can cause xAI's Grok chatbot to exfiltrate a user's…
Tag: Grok
AI Recommendation Poisoning: How ‘Ask AI’ Buttons Silently Alter LLM Memory
A new class of prompt injection attack, dubbed "AI Recommendation Poisoning," is spreading across commercial websites. It exploits pre-filled deep links in…
Adversa AI Discloses Cryptographic Context Injection Attack
Adversa AI, an AI security company, disclosed a novel attack technique called Cryptographic Context Injection that can exfiltrate private data from AI…
Malicious JetBrains Plugins Steal AI API Keys; Chrome Extensions Capture Chatbot Chats
Cybersecurity researchers have uncovered a coordinated malware campaign on the JetBrains Marketplace involving 15 malicious plugins that exfiltrate AI provider API keys.…
xAI’s Grok Vulnerable to Cryptographic Context Injection
xAI's Grok chatbot is vulnerable to a Cryptographic Context Injection attack that allows malicious web pages to steal user data. The attack…
Grok Chatbot Data Exfiltration via Cryptographic Context Injection
Grok, xAI's chatbot, is susceptible to a Cryptographic Context Injection attack that can leak user data to attacker-controlled servers. The attack exploits…