---
title: "技能不是孤岛：衡量Agent技能供应链中的依赖与风险"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.01136v1"
permalink: "https://feed.astralor.com/items/itm_8dbe57488803264e3afbf667"
published: "2026-07-01T16:21:49.000Z"
score: 59
channel: "ai"
tags: ["Agent技能供应链","SkillDepAnalyzer","依赖图","安全风险"]
---

# 技能不是孤岛：衡量Agent技能供应链中的依赖与风险

## 速览

大型语言模型（LLM）代理的技能包在快速增长中，其身份、版本和来源信息模糊不清，导致重复依赖和安装不一致。本文引入Agent技能供应链（ASSCs）概念，借鉴软件物料清单（SBOM）设计SkillDepAnalyzer，从自然语言中提取依赖证据并建模依赖图。在SKILL-DEP基准上，该方法优于LLM基线及传统SBOM工具，准确恢复技能元数据和依赖图。对超过143万个技能的分析揭示了四种结构模式，并发现技能依赖中隐藏的安全风险，可检测到已知恶意技能。研究建议引入类型化依赖清单、依赖簇管理等改进措施。

## 关键点

- 提出Agent技能供应链（ASSC）概念，形式化表达技能-包-服务混合依赖图。
- 设计SkillDepAnalyzer，从自然语言中提取依赖证据，准确恢复元数据和依赖图。
- 基于143万+技能的分析发现四种结构模式，揭示依赖中隐藏的安全风险。
- 建议类型化依赖清单、依赖簇管理和锁文件记录以提升供应链安全。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_8dbe57488803264e3afbf667