Securing Multi-Agent GIS Systems: Risk Evaluation and Prompt Hardening Optimization

Abstract:Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex conversational and spatial analysis but introduces security risks. This work presents a security-oriented framework for risk identification, evaluation, and mitigation in a multi-agent GIS system while maintaining adaptability to broader agentic architectures. We test the agentic system of a commercial geospatial partner while developing a modular state-machine-based orchestration framework that abstracts agent behavior into reusable components. We evaluate robustness using a red-teaming framework with an adaptive attacker LLM and a deterministic judge that produces binary outcomes with supporting rationales across multi-turn attacks. We further improve resilience with a prompt optimization framework that treats prompts as structured signatures and injects adversarial demonstrations, enabling systematic security improvements without degrading task performance.

Kyle Gao and Pranavi Kotta contributed equally to this work. Accepted for publication in IEEE Geoscience and Remote Sensing Letters

Cryptography and Security (cs.CR); Computation and Language (cs.CL)

arXiv:2606.17092 [cs.CR]

(or arXiv:2606.17092v2 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2606.17092 Focus to learn more arXiv-issued DOI via DataCite

https://doi.org/10.1109/LGRS.2026.3726972 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.