[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84616-en":3,"doc-seo-84616-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84616,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Skills Are Not Islands Measuring Dependency and Risk in Agent Skill Supply Chains","Agent skills package reusable operational knowledge for LLM agents, yet scaling scope turns them into dependency-bearing artifacts whose identity, version, and provenance are often implicit. This hidden structure already triggers duplicated dependencies, inconsistent installations, and a dependency-management gap. The study proposes Agent Skill Supply Chains (ASSCs) and builds SkillDepAnalyzer (SDA) to extract natural-language dependency evidence and model skills as SBOM-like artifacts. On the SKILL-DEP benchmark, SDA reconstructs complete dependency graphs with strong accuracy, then analyzes 1.43M skills to reveal risk-relevant structural patterns and hidden malicious skills across dependencies.","Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains  \nChangguo Jia∗ , Tianqi Zhao†, Runzhi He∗ , and Minghui Zhou∗  \n∗ Peking University, Beijing, China †Zhongguancun Laboratory, Beijing, China  \n[jiachangguo@stu.pku.edu.cn](jiachangguo@stu.pku.edu.cn), [zhaotq@zgclab.edu.cn](zhaotq@zgclab.edu.cn), [rzhe@pku.edu.cn](rzhe@pku.edu.cn), [zhmh@pku.edu.cn](zhmh@pku.edu.cn)  \nCorresponding author: Minghui Zhou ([zhmh@pku.edu.cn](zhmh@pku.edu.cn))  \narXiv :2607 .0 1 136v 1 [ cs . SE] 1 Jul 2026  \nAbstract—Agent skills package reusable operational knowledge for Large Language Model (LLM) agents-but as they grow in scope, they become dependency-bearing artifacts whose identities, versions, and provenance remain largely implicit. This opacity is not merely inconvenient: it already manifests as duplicated dependencies and inconsistent installations across the community, exposing a gap that dependency management has yet to close. In this study, we set out to study the intricacies of the dependencies contained in the agent skills (mixed skill-package-service dependencies) through introducing Agent Skill Supply Chains (ASSCs), expecting to help close this gap. Borrowing the idea of Software Bill of Materials (SBOMs), we design SkillDepAnalyzer (SDA) to capture natural-language dependency evidence and model skills as dependency-bearing artifacts. On SKILL-DEP benchmark, SDA recovers skill metadata and whole dependency graphs accurately and comprehensively, substantially outperforming an LLM-based baseline and package-centric SBOM tools. Applying SDA to over 1.43 million skills, we obtain the ASSCs and explore their structural diversity and security signals. We find four structural patterns: skill metadata is activation-ready but governance-poor; dependency graphs span skill, package, and service dependencies with concentrated reuse; recursive skill reuse expands dependency graphs and creates hidden package dependency inventory; and skill dependency clusters are formed around related workflows. We also find that inspecting a skill document alone is insufficient because security-relevant signals may hide in its dependencies. By analyzing ASSCs, we identify and report known malicious skills persisting in ASSCs to their developers. Based on these findings, we recommend typed dependency manifests, first-class dependency-cluster management, risk-warning audit commands for skill infrastructure maintainers (e.g., developers of skill package managers and maintainers of skill registries), and lockfilelike records for skill developers.  \nIndex Terms—agent skills, bill of materials, agent skill supply chain  \nI. INTRODUCTION  \nAgent skills encapsulate reusable operational knowledge that enables Large Language Model (LLM) agents to perform specialized tasks [1]–[3] . A typical skill packages front matter, natural-language instructions, and code scripts, which together specify how such tasks are performed. To date, the number of publicly available skills has reached 1.43 million, representing a ninefold increase in just three months [4] . These skills span diverse domains, including networking, finance, data analysis, and software development. To avoid reinventing existing capabilities, developers increasingly compose new skills by reusing existing skills, software packages, and external services. Such widespread reuse accelerates skill development,  \nbut it also introduces layered dependencies, transforming skills from isolated files into dependency-bearing artifacts.  \nHowever, existing dependency-management mechanisms have not kept pace with this emerging reuse practice. Rather than being explicitly declared, skill dependencies are implicitly scattered across metadata, instructions, and scripts. Consequently, developers cannot reliably identify a skill’s dependencies, determine their versions, or trace their provenance.  \nRecent community reports show that this opacity already causes practical dependency-management proble","cbCaioZl2YsqI6lX","https://ap.wps.com/l/cbCaioZl2YsqI6lX","pdf",1037259,1,11,"English","en",105,"# Abstract\n# Introduction\n## Background: agent skills as reusable operational knowledge\n## Problem: implicit, scattered dependencies and weak provenance tracking\n## Proposal: Agent Skill Supply Chains (ASSCs)\n## Tooling: SkillDepAnalyzer (SDA) and benchmark evaluation","[{\"question\":\"What motivates the paper’s focus on dependencies in agent skill supply chains?\",\"answer\":\"Agent skills encapsulate reusable operational knowledge, but their scope expansion makes them dependency-bearing artifacts with identities, versions, and provenance that are often implicit. This opacity leads to duplicated dependencies, inconsistent installations, and practical dependency-management issues in the community.\"},{\"question\":\"How does the paper model Agent Skill Supply Chains (ASSCs)?\",\"answer\":\"ASSCs are represented as directed dependency graphs where nodes include skills, software packages, and external services, and edges represent dependency relationships. The model makes previously implicit skill dependencies explicit for provenance tracing, component maintenance, and transitive risk auditing.\"},{\"question\":\"What does SkillDepAnalyzer (SDA) do and how is it evaluated?\",\"answer\":\"SDA automatically analyzes agent skills by recovering candidate direct dependencies from skill front matter and bodies, then assessing confidence for each candidate. On the SKILL-DEP benchmark, SDA recovers skill metadata and whole dependency graphs accurately and comprehensively, outperforming an LLM-based baseline and package-centric SBOM tools.\"}]",1784197142,28,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"skills-are-not-islands-measuring-dependency-and-risk-in-agent-skill-supply-chains","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/skills-are-not-islands-measuring-dependency-and-risk-in-agent-skill-supply-chains/84616/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What motivates the paper’s focus on dependencies in agent skill supply chains?","Question",{"text":75,"@type":76},"Agent skills encapsulate reusable operational knowledge, but their scope expansion makes them dependency-bearing artifacts with identities, versions, and provenance that are often implicit. This opacity leads to duplicated dependencies, inconsistent installations, and practical dependency-management issues in the community.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the paper model Agent Skill Supply Chains (ASSCs)?",{"text":80,"@type":76},"ASSCs are represented as directed dependency graphs where nodes include skills, software packages, and external services, and edges represent dependency relationships. The model makes previously implicit skill dependencies explicit for provenance tracing, component maintenance, and transitive risk auditing.",{"name":82,"@type":73,"acceptedAnswer":83},"What does SkillDepAnalyzer (SDA) do and how is it evaluated?",{"text":84,"@type":76},"SDA automatically analyzes agent skills by recovering candidate direct dependencies from skill front matter and bodies, then assessing confidence for each candidate. On the SKILL-DEP benchmark, SDA recovers skill metadata and whole dependency graphs accurately and comprehensively, outperforming an LLM-based baseline and package-centric SBOM tools.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]