Skip to content
Search
paperMay 2026Unreviewed

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection

Chia-Pei, Chen, Kentaroh Toyoda, Anita Lai, Alex Leung

View resourcePDF

Abstract

Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still influence them by embedding hidden instructions in the HTML pages those domains serve. Existing red-teaming resources fall short of this scenario: prompt-injection benchmarks ship pre-built adversarial pages that whitelisted agents cannot reach, and generic LLM scanners probe the model API rather than its retrieved content. We present IPI-proxy, an open-s

Categories

Prompt InjectionRed TeamingBenchmarks & Evaluation

Framework mappings

OWASP Top 10 for LLM Applications
  • LLM01Prompt Injection
MITRE ATLAS
  • AML.T0051LLM Prompt Injection
NIST AI Risk Management Framework
  • MEASUREMeasure

Suggested from the entry's categories.

Cite

@misc{chiapei2026ipiproxy,
  title = {{IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection}},
  author = {Chia-Pei and Chen and Kentaroh Toyoda and Anita Lai and Alex Leung},
  year = {2026},
  month = may,
  eprint = {2605.11868},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.11868}
}