Researchers Uncover New Attack Surfaces in Vision-Language Model-Powered Mobile Agents

Jul 15, 2026

A new preprint identifies two novel attack surfaces—Screen Perception and Misused Channel—in third-party mobile agents powered by Vision-Language Models (VLMs). The researchers demonstrate seven concrete attacks, showing that malicious apps can hijack agent actions and execute arbitrary commands without requiring permissions, all while remaining visually indistinguishable to users.

Why it matters: This work exposes a fundamental security risk in the design of autonomous mobile agents, emphasizing the need for new security models on multi-tenant platforms.

Full story at: arXiv Cryptography and Security ↗