WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation

Abstract

Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this prolonged execution process provides attackers with more opportunities to inject malicious instructions. Existing prompt injection attacks against browser agents expose two key gaps: (1) low effectiveness, as attacks optimized for toy baselines fail to achieve end-to-end goals in real-world scenarios with complex environments and longer steps; (2)

Categories

Framework mappings

Suggested from the entry's categories.

@misc{liu2026webtrap,
  title = {{WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation}},
  author = {Zhichao Liu and Wenbo Pan and Haining Yu and Ge Gao and Tianqing Zhu and Xiaohua Jia},
  year = {2026},
  month = may,
  eprint = {2605.08310},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.08310}
}