PromptSpy – First Known Android AI Malware Uses Google’s Gemini for Decision-making

The first known Android malware family to weaponize a generative AI model, specifically Google’s Gemini, as part of its active execution flow. Discovered in February 2026, the malware represents a significant evolutionary step in mobile threats and follows ESET’s earlier identification of PromptLock, the first AI-powered ransomware, in August 2025. PromptSpy, uncovered by ESET researcher […]

The post PromptSpy – First Known Android AI Malware Uses Google’s Gemini for Decision-making appeared first on Cyber Security News.