Beyond Input Guardrails: Reconstructing Cross-Agent Semantic Flows for Execution-Aware Attack Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wei, Yangyang, Xu, Yijie, Li, Zhenyuan, Shen, Xiangmin, Ji, Shouling
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915835119927296
author Wei, Yangyang
Xu, Yijie
Li, Zhenyuan
Shen, Xiangmin
Ji, Shouling
author_facet Wei, Yangyang
Xu, Yijie
Li, Zhenyuan
Shen, Xiangmin
Ji, Shouling
contents Multi-Agent System is emerging as the \textit{de facto} standard for complex task orchestration. However, its reliance on autonomous execution and unstructured inter-agent communication introduces severe risks, such as indirect prompt injection, that easily circumvent conventional input guardrails. To address this, we propose \SysName, a framework that shifts the defensive paradigm from static input filtering to execution-aware analysis. By extracting and reconstructing Cross-Agent Semantic Flows, \SysName synthesizes fragmented operational primitives into contiguous behavioral trajectories, enabling a holistic view of system activity. We leverage a Supervisor LLM to scrutinize these trajectories, identifying anomalies across data flow violations, control flow deviations, and intent inconsistencies. Empirical evaluations demonstrate that \SysName effectively detects over ten distinct compound attack vectors, achieving F1-scores of 85.3\% and 66.7\% for node-level and path-level end-to-end attack detection, respectively. The source code is available at https://anonymous.4open.science/r/MAScope-71DC.
format Preprint
id arxiv_https___arxiv_org_abs_2603_04469
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Input Guardrails: Reconstructing Cross-Agent Semantic Flows for Execution-Aware Attack Detection
Wei, Yangyang
Xu, Yijie
Li, Zhenyuan
Shen, Xiangmin
Ji, Shouling
Cryptography and Security
Multiagent Systems
Multi-Agent System is emerging as the \textit{de facto} standard for complex task orchestration. However, its reliance on autonomous execution and unstructured inter-agent communication introduces severe risks, such as indirect prompt injection, that easily circumvent conventional input guardrails. To address this, we propose \SysName, a framework that shifts the defensive paradigm from static input filtering to execution-aware analysis. By extracting and reconstructing Cross-Agent Semantic Flows, \SysName synthesizes fragmented operational primitives into contiguous behavioral trajectories, enabling a holistic view of system activity. We leverage a Supervisor LLM to scrutinize these trajectories, identifying anomalies across data flow violations, control flow deviations, and intent inconsistencies. Empirical evaluations demonstrate that \SysName effectively detects over ten distinct compound attack vectors, achieving F1-scores of 85.3\% and 66.7\% for node-level and path-level end-to-end attack detection, respectively. The source code is available at https://anonymous.4open.science/r/MAScope-71DC.
title Beyond Input Guardrails: Reconstructing Cross-Agent Semantic Flows for Execution-Aware Attack Detection
topic Cryptography and Security
Multiagent Systems
url https://arxiv.org/abs/2603.04469