paperOctober 2025Unreviewed

In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers

Avihay Cohen

arXiv.org

Abstract

Large Language Model (LLM) based agents integrated into web browsers (often called agentic AI browsers) offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where malicious instructions hidden in a webpage deceive the agent into unwanted actions. These attacks can bypass traditional web security boundaries, as the AI agent operates with the user privileges across sites. In this paper, we present a novel fuzzing framework that runs entirely in

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@misc{cohen2025inbrowser,
  title = {{In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers}},
  author = {Avihay Cohen},
  year = {2025},
  month = oct,
  eprint = {2510.13543},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2510.13543},
  url = {https://www.semanticscholar.org/paper/8b9011b256c4819d47721efc3f9522a721b92735}
}