SkillScope：面向智能体技能的细粒度最小权限强制执行

Computer Science > Cryptography and Security arXiv:2605.05868 (cs) [Submitted on 7 May 2026 (v1), last revised 10 Sep 2026 (this version, v3)] Title:SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills Authors:Jiangrong Wu, Yuhong Nan, Yixi Lin, Huaijin Wang, Yuming Xiao, Shuai Wang, Zibin Zheng View a PDF of the paper titled SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills, by Jiangrong Wu and 6 other authors View PDF HTML (experimental) Abstract:Agent Skills have become a practical way to extend LLM agents by packaging metadata, natural-language instructions, and executable resources into reusable capability bundles. However, this growing Skill ecosystem introduces a new compliance risk: a Skill may perform high-impact actions that fall outside the scope permitted by the user's current request, thereby violating least privilege. Existing skill detection approaches are insufficient for this problem because it is inherently task-conditioned: the same action may be legitimate under one user prompt but over-privileged under another. In this paper, we present SkillScope, a framework for fine-grained least-privilege enforcement in Agent Skills. SkillScope adopts a graph-based analysis approach that models instruction-level procedures and code-level operations as fine-grained action nodes. It extracts potential over-privilege candidates, validates them under graph-instantiated user tasks through runtime analysis, and constrains validated over-privileged actions via control-flow privilege constraining. We evaluate SkillScope through effectiveness experiments and large-scale real-world measurement. SkillScope achieves a 94.53% skill-level F1 score for over-privilege detection. In the wild, SkillScope validates 6,590 of 68,312 valid real-world Skills as exhibiting over-privileged behaviors, showing that least-privilege violations are prevalent in current Skill ecosystems. In the privilege-constraining evaluation, SkillScope reduces triggered over-privileged action-in-task instances by 88.56% while preserving legitimate task completion. Comments: Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2605.05868 [cs.CR] (or arXiv:2605.05868v3 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2605.05868 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yixi Lin [view email] [v1] Thu, 7 May 2026 08:34:14 UTC (1,072 KB) [v2] Mon, 7 Sep 2026 13:49:06 UTC (1,100 KB) [v3] Thu, 10 Sep 2026 12:12:32 UTC (1,099 KB) Full-text links: Access Paper: View a PDF of the paper titled SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills, by Jiangrong Wu and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR new | recent | 2026-05 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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 Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)