attack arXiv Dec 16, 2025 · Dec 2025
Yunhao Yao, Zhiqiang Wang, Haoran Cheng et al. · University of Science and Technology of China · Beijing University of Aeronautics and Astronautics
Attacks LLM agent privacy by showing semi-honest MCP servers reconstruct user intent from tool call metadata alone
Insecure Plugin Design Sensitive Information Disclosure nlp
The evolution of Large Language Models (LLMs) into Agentic AI has established the Model Context Protocol (MCP) as the standard for connecting reasoning engines with external tools. Although this decoupled architecture fosters modularity, it simultaneously shatters the traditional trust boundary. We uncover a novel privacy vector inherent to this paradigm: the Intent Inversion Attack. We show that semi-honest third-party MCP servers can accurately reconstruct users' underlying intents by leveraging only authorized metadata (e.g., function signatures, arguments, and receipts), effectively bypassing the need for raw query access. To quantify this threat, we introduce IntentMiner. Unlike statistical approaches, IntentMiner employs a hierarchical semantic parsing strategy that performs step-level intent reconstruction by analyzing tool functions, parameter entities, and result feedback in an orthogonal manner. Experiments on the ToolACE benchmark reveal that IntentMiner achieves a semantic alignment of over 85% with original queries, substantially surpassing LLM baselines. This work exposes a critical endogenous vulnerability: without semantic obfuscation, executing functions requires the transparency of intent, thereby challenging the privacy foundations of next-generation AI agents.
llm University of Science and Technology of China · Beijing University of Aeronautics and Astronautics
ML Security Papers