We present an LLM-driven framework for retrieving remote sensing data from cloud-based geospatial catalogues using natural language queries. The system converts user intent into structured API calls, enabling efficient access to satellite imagery and environmental datasets. The architecture integrates three agents: Guardrail for safety and policy enforcement, General-QA for intent interpretation, and Recommender-Analyst for schema-aware API call generation. This coordinated design ensures reliable, semantically aligned interaction with external data services. The modular framework is portable across platforms through API schema substitution and supports applications in environmental monitoring, disaster response, and climate analysis. It establishes a scalable interface between user intent and geospatial infrastructure, enabling streamlined and automated Earth observation workflows. Preliminary experiments under adversarial multi-turn settings show that prompt-level safety instructions improve robustness, although rare high-impact failures persist in API manipulation scenarios and highlight the need for adaptive, system-level defenses that balance safety, usability, and cost efficiency, which motivates the use of our intercept-level Guardrail agent.

翻译：我们提出了一种基于大语言模型的框架，用于通过自然语言查询从云端地理空间目录中检索遥感数据。该系统将用户意图转化为结构化API调用，实现对卫星影像和环境数据集的高效访问。架构集成了三个智能体：Guardrail（安全与合规保障）、General-QA（意图理解）以及Recommender-Analyst（面向模式感知的API调用生成）。这种协同设计确保了与外部数据服务间可靠且语义对齐的交互。模块化框架通过API模式替换实现跨平台移植，并支持环境监测、灾害响应和气候分析等应用。该框架在用户意图与地理空间基础设施之间建立了可扩展的接口，从而实现了精简且自动化的地球观测工作流。在对抗性多轮对话场景下的初步实验表明，提示级安全指令能够提升鲁棒性，但API操控场景中仍存在罕见的高影响失效模式，这凸显了建立自适应、系统级防御机制的需求，以平衡安全性、可用性与成本效率，这也促使我们采用拦截级Guardrail智能体方案。