arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.03024cs.CRcs.SE
收藏

SkillGuard:一种面向智能体技能的权限框架

SkillGuard: A Permission-Centric Framework for Agent Skill Security

CSIRO(联邦科学与工业研究组织);Australian National University(澳大利亚国立大学)

Shidong Pan, Xiaoyu Sun, Tianyi Zhang, Dianshu Liao, Kaiwen Yang, Zhenchang Xing

AI总结:

提出SkillGuard权限框架,通过双平面治理模型联合管控上下文影响和动作副作用,以缩小技能声明意图与运行时行为之间的安全差距。

摘要:

智能体技能通过可复用的指令、脚本、工具绑定和上下文依赖扩展了LLM智能体。然而,当前的技能生态系统主要依赖基于信任的加载和静态检查,在技能可以注入到智能体上下文的内容与其在运行时可能导致智能体执行的操作之间存在差距。这种差距引入了新的安全和隐私风险,现有防御措施主要静态检查技能文件或监管单个工具调用,未能系统地将技能的声明意图与其运行时行为联系起来。在本文中,我们提出了SkillGuard,一种以技能为中心的权限框架,将技能视为携带权限的可执行工件。SkillGuard引入了一种双平面治理模型,通过技能清单、运行时访问控制、用户中介授权、默认拒绝执行、能力推断和行为监控,联合管控上下文影响和动作副作用。我们在315个真实技能和SkillInject上评估了SkillGuard。权限分类覆盖了99.76%的观察到的受保护对象,自动清单生成达到了91.0%的F1值。在对抗性评估中,SkillGuard将上下文注入的攻击成功率从32.37%降低到23.02%,将明显注入的攻击成功率从25.56%降低到16.67%,同时保持了良性任务的效用。这些结果表明,SkillGuard作为一种以技能为中心的权限框架,可以为提高智能体技能生态系统的隐私和安全性提供实用基础。

英文摘要:

Skills extend LLM agents with reusable instructions, scripts, data, and tool bindings. This shift makes skills a new security principal in agent systems: a skill can alter the agent's reasoning before any tool is called, and it can also steer the agent toward actions with concrete side effects. However, current skill ecosystems lack a permission model that captures this dual role. Existing defenses either inspect skill files before use or constrain individual tool calls during execution, leaving the connection between skill-level intent, contextual influence, and runtime behavior weakly governed. In this paper, we present SkillGuard, a skill-centric permission framework that treats skills as permission-bearing executable artifacts. SkillGuard introduces a dual-plane governance model that jointly regulates context influence and action side effects through skill manifests, runtime permission control, user interaction, and policy enforcement. We evaluate the permission taxonomy expressiveness on 1,260 real-world skills, and 99.93% of observed protected objects are covered. In adversarial evaluations on SkillInject dataset, SkillGuard reduces attack success rate from 35.3% to 20.7% for contextual injections and from 36.7% to 18.0% for obvious injections, while decently maintaining benign task completion. These results suggest that SkillGuard, as a skill-centric permission framework, can provide a practical foundation for improving the security of agent skill ecosystems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑