Malicious AI browser extensions collected LLM chat histories and browsing data from platforms such as ChatGPT and DeepSeek.
Researchers disclosed a HashJack attack that manipulates AI browsers. Cato CTRL examined Comet, Copilot for Edge, and Gemini for Chrome. Could lead to data theft, phishing, and malware downloads.
Researchers discovered that adding instructions for AI-powered browser assistants after the hash (#) symbol inside URLs can influence their behavior to leak sensitive data and direct users to phishing ...