The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration

Sam Johnson, Viet Pham, Thai Le. The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration. In Ivan Habernal, Peter Schulam 0001, Jörg Tiedemann, editors, Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025 - System Demonstrations, Suzhou, China, November 4-9, 2025. pages 729-738, Association for Computational Linguistics, 2025. [doi]

Authors

Sam Johnson

This author has not been identified. Look up 'Sam Johnson' in Google

Viet Pham

This author has not been identified. Look up 'Viet Pham' in Google

Thai Le

This author has not been identified. Look up 'Thai Le' in Google