Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents

This paper analyzes backdoor attacks against generic LLM-based agents, including attacks that trigger from user queries or intermediate observations and attacks that alter intermediate reasoning while preserving the final answer. It matters for GUI work because web-shopping agents are one evaluation setting, but the contribution is a broader LLM-agent security analysis rather than a GUI-specific study.

• Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System
  February 11, 2026 · arXiv