AI security company Zenity has disclosed the details of two AI browser hacking techniques targeting Claude in Chrome and ChatGPT Atlas, demonstrating how they can be used for account takeovers, phishing, and making unauthorized Amazon purchases.
Zenity described its research in two separate blog posts published on Wednesday, one covering the ChatGPT Atlas research and one covering the Claude in Chrome attack.
ChatGPT Atlas hacking
Zenity researchers discovered that OpenAI’s agentic browser, ChatGPT Atlas, is vulnerable to zero-click indirect prompt injection (IPI) due to fundamental architectural design issues rather than traditional software bugs.
By exploiting ‘intent collision’ through a single planted comment on an X thread, researchers demonstrated how an attacker can hijack benign user requests to control the agent across authenticated web sessions.
