WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911371760762880 |
|---|---|
| author | Wu, Xinyi Chen, Jiagui Hong, Geng Dong, Jiayi Pan, Xudong Dai, Jiarun Yang, Min |
| author_facet | Wu, Xinyi Chen, Jiagui Hong, Geng Dong, Jiayi Pan, Xudong Dai, Jiarun Yang, Min |
| contents | Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present WebTrap Park, an automated platform for systematic security evaluation of Web Agents through direct observation of their concrete interactions with live web pages. WebTrap Park instantiates three major sources of security risk into 1,226 executable evaluation tasks and enables action based assessment without requiring agent modification. Our results reveal clear security differences across agent frameworks, highlighting the importance of agent architecture beyond the underlying model. WebTrap Park is publicly accessible at https://security.fudan.edu.cn/webagent and provides a scalable foundation for reproducible Web Agent security evaluation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_08406 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents Wu, Xinyi Chen, Jiagui Hong, Geng Dong, Jiayi Pan, Xudong Dai, Jiarun Yang, Min Artificial Intelligence Cryptography and Security Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present WebTrap Park, an automated platform for systematic security evaluation of Web Agents through direct observation of their concrete interactions with live web pages. WebTrap Park instantiates three major sources of security risk into 1,226 executable evaluation tasks and enables action based assessment without requiring agent modification. Our results reveal clear security differences across agent frameworks, highlighting the importance of agent architecture beyond the underlying model. WebTrap Park is publicly accessible at https://security.fudan.edu.cn/webagent and provides a scalable foundation for reproducible Web Agent security evaluation. |
| title | WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents |
| topic | Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2601.08406 |