WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912873600516096 |
|---|---|
| author | Wang, Xilong Liu, Yinuo Wang, Zhun Song, Dawn Gong, Neil |
| author_facet | Wang, Xilong Liu, Yinuo Wang, Zhun Song, Dawn Gong, Neil |
| contents | Prompt injection attacks manipulate webpage content to cause web agents to execute attacker-specified tasks instead of the user's intended ones. Existing methods for detecting and localizing such attacks achieve limited effectiveness, as their underlying assumptions often do not hold in the web-agent setting. In this work, we propose WebSentinel, a two-step approach for detecting and localizing prompt injection attacks in webpages. Given a webpage, Step I extracts \emph{segments of interest} that may be contaminated, and Step II evaluates each segment by checking its consistency with the webpage content as context. We show that WebSentinel is highly effective, substantially outperforming baseline methods across multiple datasets of both contaminated and clean webpages that we collected. Our code is available at: https://github.com/wxl-lxw/WebSentinel. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03792 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents Wang, Xilong Liu, Yinuo Wang, Zhun Song, Dawn Gong, Neil Cryptography and Security Artificial Intelligence Computation and Language Prompt injection attacks manipulate webpage content to cause web agents to execute attacker-specified tasks instead of the user's intended ones. Existing methods for detecting and localizing such attacks achieve limited effectiveness, as their underlying assumptions often do not hold in the web-agent setting. In this work, we propose WebSentinel, a two-step approach for detecting and localizing prompt injection attacks in webpages. Given a webpage, Step I extracts \emph{segments of interest} that may be contaminated, and Step II evaluates each segment by checking its consistency with the webpage content as context. We show that WebSentinel is highly effective, substantially outperforming baseline methods across multiple datasets of both contaminated and clean webpages that we collected. Our code is available at: https://github.com/wxl-lxw/WebSentinel. |
| title | WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents |
| topic | Cryptography and Security Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2602.03792 |