ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems
This addresses a critical security gap for developers and users of LLM agent systems by providing a comprehensive benchmark and effective detection method for emerging supply-chain threats.
The paper tackles the problem of supply-chain threats in LLM agent systems where malicious behaviors are embedded in third-party tools, introducing SC-Inject-Bench, a benchmark with over 10,000 malicious MCP tools, and ShieldNet, a network-level guardrail framework that achieves up to 0.995 F-1 score with only 0.8% false positives.
Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on third-party tools and MCP servers, a new class of supply-chain threats has emerged, where malicious behaviors are embedded in seemingly benign tools, silently hijacking agent execution, leaking sensitive data, or triggering unauthorized actions. Despite their growing impact, there is currently no comprehensive benchmark for evaluating such threats. To bridge this gap, we introduce SC-Inject-Bench, a large-scale benchmark comprising over 10,000 malicious MCP tools grounded in a taxonomy of 25+ attack types derived from MITRE ATT&CK targeting supply-chain threats. We observe that existing MCP scanners and semantic guardrails perform poorly on this benchmark. Motivated by this finding, we propose ShieldNet, a network-level guardrail framework that detects supply-chain poisoning by observing real network interactions rather than surface-level tool traces. ShieldNet integrates a man-in-the-middle (MITM) proxy and an event extractor to identify critical network behaviors, which are then processed by a lightweight classifier for attack detection. Extensive experiments show that ShieldNet achieves strong detection performance (up to 0.995 F-1 with only 0.8% false positives) while introducing little runtime overhead, substantially outperforming existing MCP scanners and LLM-based guardrails.