$S^3$: Improving Agent Safety through Multi-Stage Defense

Computer Science > Cryptography and Security [Submitted on 3 Aug 2026] S 3 : Improving Agent Safety through Multi-Stage Defense Zibo Xiao, Haoyu Wang, Jun Sun Large Language Model (LLM) agents rely on multi-stage agentic workflows, with stages such as memory, planning, and tool execution, to accomplish complex tasks. However, risks may emerge at different stages, propagate across steps, and become difficult to detect and mitigate. Existing safety methods protect only isolated stages and are difficult to integrate, leaving agents without comprehensive protection throughout the workflow. To address these limitations, we introduce Stage-Specific Safety Skills, a unified abstraction that represents heterogeneous safety designs as reusable and composable components with explicit stage semantics. We further develop an automated transformation pipeline that converts existing safety designs into reusable safety skills and establish a community-driven safety skill library. Building on this abstraction, we propose S 3 , a multi-stage defense framework in which a guard agent orchestrates stage-specific safety skills for risk detection and mitigation throughout the agentic workflow. We also construct the Multi-Stage Risk Benchmark (MSRB) to evaluate representative risks across workflow stages. Experimental results show that S 3 consistently outperforms representative state-of-the-art baselines in both safety effectiveness and utility preservation. These results demonstrate the potential of stage-specific safety skills as a scalable and composable foundation for building resilient and trustworthy agent systems. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2608.02683 [cs.CR]   (or arXiv:2608.02683v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.02683 Focus to learn more Submission history From: Zibo Xiao [view email] [v1] Mon, 3 Aug 2026 02:06:06 UTC (119 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-08 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)