AI-generated

Security researchers have identified a new Android Trojan named PromptSpy that uses generative AI technology to enhance its persistence on compromised devices. Discovered by ESET researchers, PromptSpy leverages Google's Gemini AI model to analyze infected device screens and generate tailored instructions for embedding itself within recent apps lists. It includes a Virtual Network Computing (VNC) module that allows attackers full remote control over the device, enabling activities such as viewing the screen, performing actions remotely, capturing lock screen data, blocking uninstallation attempts, gathering device information, taking screenshots, and recording screen activity as video. The malware communicates with command-and-control servers using AES encryption and exploits Android Accessibility Services, making it difficult to remove. PromptSpy is distributed through a dedicated website and is financially motivated, adapting to various Android interfaces and operating system versions. ESET's analysis indicates that the malware is regionally targeted, with a focus on Argentina, and may have been developed in a Chinese-speaking environment. The same threat actor is believed to be responsible for both VNCSpy and PromptSpy.