collaborators

1 paper

cs.CR2026

LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web Agents

Longtao Guo, Zelin Zhang, Kaifeng Huang +1

LLM-based web agents automate user tasks by observing webpages and executing browser actions on behalf of users. As these agents operate on real web services, login becomes a sensi…