Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains

Source

arXiv

arxiv.org/abs/2607.01136v1

Read the source

Source

Plain-Language Brief

Researchers introduce a new method called Agent Skill Supply Chains (ASSCs) to manage dependencies in Large Language Model agents. They develop SkillDepAnalyzer, which extracts dependency graphs and metadata from skills more accurately than current methods. Using this tool on over 1.43 million skills, they discover patterns in ASSCs such as the prevalence of skill reuse and hidden dependencies. They also identify known malicious skills and recommend measures to improve security and manage risks.

What the Document Says

  • Agent Skill Supply Chains (ASSCs) are introduced to characterize dependency graphs for Large Language Model agents.
  • SkillDepAnalyzer is designed to capture natural-language dependency evidence and model skills as dependency-bearing artifacts.
  • On the SKILL-DEP benchmark, SkillDepAnalyzer outperforms an LLM-based baseline and package-centric SBOM tools.
  • Applying SkillDepAnalyzer to over 1.43 million skills reveals four structural patterns in ASSCs: activation-ready but governance-poor skill metadata; concentrated reuse of dependencies spanning skills, packages, and services; recursive skill reuse expanding dependency graphs and creating hidden package inventory; and formation of skill dependency clusters around related workflows.
  • Inspection of a single skill misses security-relevant signals hiding in its dependencies.
  • By analyzing ASSCs, known malicious skills are identified and reported to their developers.
  • Recommendations for improvement include typed dependency manifests, first-class dependency-cluster management, risk-warning audit commands, and lockfile-like records.

Key Concepts Mentioned

  • Agent Skill Supply Chains (ASSCs)
  • SkillDepAnalyzer
  • Large Language Model (LLM) agents
  • dependency graphs
  • Software Bill of Materials (SBOMs)
  • SKILL-DEP benchmark
  • skill metadata
  • package dependencies
  • service dependencies
  • recursive skill reuse
  • hidden package inventory
  • skill dependency clusters
  • malicious skills

Claims Made by the Document

  • SkillDepAnalyzer outperforms existing methods in recovering skill metadata and dependency graphs.
  • Four structural patterns are identified in ASSCs.
  • Inspection of a single skill misses security-relevant signals hiding in its dependencies.

Evidence Used

  • Results from the SKILL-DEP benchmark
  • Analysis of over 1.43 million skills

Methods / Approach

  • Design and implementation of SkillDepAnalyzer
  • Analysis of dependency graphs and metadata

Limitations Stated by the Authors

  • Not stated in the source

Limitations Noted by the Agent

Agent interpretation — not from the source.

  • The data used for testing may not represent real-world scenarios perfectly.
  • The performance of SkillDepAnalyzer may vary with different types of Large Language Model agents.

Open Questions

  • What is the impact of SkillDepAnalyzer on the overall performance of Large Language Model agents?
  • How well does SkillDepAnalyzer handle complex dependencies and relationships among skills?

Notes for Future Q&A

May include interpretation. Labeled where it does.

  • The text focuses primarily on the introduction and evaluation of Agent Skill Supply Chains (ASSCs) and SkillDepAnalyzer. It also discusses findings from their analysis but does not provide detailed information about potential limitations or open questions.

Raw Abstract / Excerpt

Agent skills package reusable operational knowledge for Large Language Model (LLM) agents, yet as they grow in scope, they become dependency-bearing artifacts whose identities, versions, and provenance remain implicit. This opacity already causes duplicated dependencies and inconsistent installations, exposing a gap that dependency management has yet to close. We introduce Agent Skill Supply Chains (ASSCs) to characterize mixed skill-package-service dependency graphs and help close this gap. Borrowing from Software Bill of Materials (SBOMs), we design SkillDepAnalyzer to capture natural-language dependency evidence and model skills as dependency-bearing artifacts. On the SKILL-DEP benchmark, SkillDepAnalyzer recovers skill metadata and dependency graphs accurately and comprehensively, substantially outperforming an LLM-based baseline and package-centric SBOM tools. Applying SkillDepAnalyzer to over 1.43 million skills, we obtain 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 inventory; and skill dependency clusters form around related workflows. We also find that inspecting a skill alone misses security-relevant signals hiding 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, and lockfile-like records for skill developers.