arXiv · 2610.12524
An Exploration of Attacks on AI Agent Systems
Abstract
As autonomous AI agents become more integrated into sensitive domains, it is crucial that single and multi-agent AI systems are secured. This paper investigates how prompt injection attacks can exploit both direct user inputs and inter?agent communication to leak sensitive information and trigger cross-agent infections. While our tests mostly highlight key vulnerabilities in single-agent systems, we also extend these attacks to multi-agent frameworks, investigating how weaknesses can propagate across agents. Our findings emphasize the need for more robust defenses as AI agents become more commonly embedded in real-world workflows.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Cathleen Qiao, Layah Vigneaud, Chloe Brandon, Max Cabilangan, Xiyuan Cao, Isaac Khabra, Reva Mahajan, Lena Nguyen, Kyle Pak, Anagh Pandya, Roshni Dave, Peiran Wang. 2026-10-08. An Exploration of Attacks on AI Agent Systems. https://arxiv.org/abs/2610.12524
Cite the original work for its findings. Save a collection to share your selection of sources.