4 web applications

Emerging

1papers using it

2026first seen

The '4 web applications' dataset/benchmark contains a set of web applications used to evaluate the security of large language model-based web agents against indirect prompt injection attacks.

🔎 Find this dataset

Papers using 4 web applications (1)

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks2026