SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents

Abstract

Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into webpage content to induce unintended actions. This threat is further amplified for screenshot-based web agents, which operate on rendered visual webpages rather than structured textual representations, making predominant text-centric defenses ineffective. Although multimodal detection methods have been

Categories

Framework mappings

Suggested from the entry's categories.

@misc{du2026snapguard,
  title = {{SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents}},
  author = {Mengyao Du and Han Fang and Haokai Ma and Jiahao Chen and Kai Xu and Quanjun Yin and Ee-Chien Chang},
  year = {2026},
  month = apr,
  eprint = {2604.25562},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.25562}
}