An automated transformation pipeline that converts existing safety designs into reusable safety skills and establish a community-driven safety skill library is developed and results demonstrate the potential of stage-specific safety skills as a scalable and composable foundation for building resilient and trustworthy agent systems.
Abstract
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.
A unified systems foundation and reference architecture for the agentic skills ecosystem is established, formalize skills as externalized procedural knowledge bridging high-level cognitive planning with deterministic execution environments, and systematically delineate the architecture across a nine-stage lifecycle.
Sanket Badhe, D. Shah, Priyanka Tiwari et al.· 3 citations· ⚡1
Recently, the rapid development of large language models (LLMs) has reshaped software engineering by enabling autonomous code agents that plan, execute, and utilize external tools iteratively to tackle complex tasks. Beyond achieving functional correctness, these agents must faithfully follow process instructions and c...
Safety Harness Evolution (SHE) is proposed, a framework that learns evolving safe boundaries from rollout trajectories and introduces an attribution-guided evolution loop that converts trajectory failures into structured diagnoses, learns artifact-specific boundary refinements, and selects evolved harnesses through saf...
Wanying Qu, Qing-Hua Mao, Yu Li et al.· 5 citations
This work presents ComponentBench, a benchmark and diagnostic pipeline for component-level evaluation of computer-use agents on modern web UIs, and introduces a scalable pipeline for auditing realized structural difficulty after implementation and synthesizing structured failure analyses across tasks and component fami...
Tian-Chen Guan, Xinlei Lin, Royce Cheng-Yue et al.· 0 citations
This work proposes control-data flow separation, where execution-critical control is represented as typed, validated program objects, while task-relevant language remains the optimizable data flow for agent communication.
Wentao Zhang, S. Murtaza, Junaid Ahmad Bhatti et al.· 0 citations
Unlike conventional software systems and large language models (LLMs) evaluated in isolation, LLM-based agentic systems introduce a compositional, workflow-level attack surface. Existing security analysis approaches provide limited support for identifying security omissions implicit in functional use case flows and der...
Guang-Yu Wang, Bangqi Li, Ji Wu et al.· Electronics· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.