Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains
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-langua
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownagent-tools →
- LinkedLinked via unknownIEEE Rolls Out Large Language Models Virtual Training Course →
- LinkedLinked via unknownOpen-source agent framework crosses 50k stars →
- PossiblePossibly related (embedding) · 57%langchain-ai/langgraphjs →
- LinkedLinked via arxiv author · 85%Changguo Jia →
“Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains”
- LinkedLinked via arxiv author · 85%Tianqi Zhao →
“Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains”
- LinkedLinked via arxiv author · 85%Runzhi He →
“Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains”
- LinkedLinked via arxiv author · 85%Minghui Zhou →
“Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains”