Token导航 LogoToken导航TokenDH.com
待分类权限需确认github未标认证来源可访问许可证需确认审计未展示

supply-chain-auditsupply chain 审核

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

494

周安装

20

GitHub Stars

55

下载量

155
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:supply-chain-audit(supply chain 审核)
来源仓库:https://github.com/rysweet/amplihack
仓库路径:skills/supply-chain-audit
安装命令:
npx skills add https://github.com/rysweet/amplihack --skill supply-chain-audit
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/rysweet/amplihack --skill supply-chain-audit

简介

supply-chain-audit 用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。

  • 适合梳理敏感配置、检查依赖风险或生成安全复核清单,支持供应链安全场景。
  • 可分析鉴权逻辑和依赖关系,但不能把工具输出直接当作最终结论。
  • 涉及密钥、令牌或生产系统时,应先确认最小权限和操作边界。
  • 需结合脱敏方式和权限控制,避免对实际系统造成影响。

SKILL.md

Supply Chain Audit

Audits software supply chain security across 12 dimensions: GitHub Actions SHA pinning, workflow permissions, secrets scanning, cache poisoning, container image digests, OIDC credentials, and ecosystem lock files.

Quick Start

"supply chain audit"
→ Full audit at repo root, all detected ecosystems

"check action pinning"
→ GitHub Actions dimensions only (1-4)

"audit dependencies in ./services/api"
→ Scoped to a subdirectory

"CI security audit --scope gha,containers"
→ Dimensions 1-5, 12 only

What It Audits

ScopeEcosystemsDimensions
ghaGitHub Actions1: SHA pinning, 2: permissions, 3: secrets, 4: cache
containersDocker5: image digests, 12: build chain
credentialsCI secrets6: OIDC migration
dotnetNuGet7: lock files, source mapping
pythonpip/PyPI8: hash pinning, typosquatting
rustCargo9: Cargo.lock, build.rs, [patch]
nodenpm/yarn10: npm ci, npx, postinstall
goGo modules11: go.sum, GONOSUMCHECK, replace

Output

Produces a structured markdown report with:

  • Severity summary (Critical / High / Medium / Info)
  • Findings with file:line references and ready-to-use fix templates
  • SLSA readiness assessment
  • Handoffs to dependency-resolver and pre-commit-manager

Example finding:

CRITICAL-001 · Dim 1 · Unpinned third-party action File: .github/workflows/release.yml:14 Current: uses: actions/checkout@v4 Expected: uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2 Fix: https://github.com/actions/checkout/releases Why: Mutable semver tag allows silent code replacement without any file change in your repo — a direct supply-chain compromise vector.

Configuration

Accepted Risks

Create .supply-chain-accepted-risks.yml to suppress findings that are intentionally accepted:

- id: HIGH-002 file: .github/workflows/ci.yml line: 47 dimension: 1 rationale: "Pinning blocked by upstream; tracked in GH-4521" review_date: "2026-06-01"

Constraints: 64KB file cap; no wildcards; Critical findings cannot be suppressed; past review_date restores original severity.

Integration Points

SkillTrigger
dependency-resolverMissing or drifted lock files (Dims 7-11)
pre-commit-managerAlways — installs SHA-pinning and audit hooks
silent-degradation-auditCI security steps that suppress failures
cybersecurity-analystRuntime exposure beyond supply chain scope

Documentation

FileContents
SKILL.mdWorkflow, scope flags, accepted-risks protocol
reference/contracts.mdFinding schema, report schema, handoff templates
reference/actions.mdDims 1-4: GHA pinning, permissions, secrets, cache
reference/containers.mdDims 5, 12: Image digests, build chain
reference/credentials.mdDim 6: OIDC migration
reference/dotnet.mdDim 7: NuGet lock files
reference/python.mdDim 8: pip hash pinning
reference/rust.mdDim 9: Cargo supply chain
reference/node.mdDim 10: npm/yarn integrity
reference/go.mdDim 11: Go module integrity
reference/sbom-slsa.mdSBOM generation, SLSA compliance, cosign
reference/eval-scenarios.mdEvaluation scenarios and pass/fail criteria

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.41%
按下载量换算52

Claude

29.54%
按下载量换算46

Cursor

17.19%
按下载量换算27

Gemini CLI

10.06%
按下载量换算16

安全审计

暂无安全审计结果可展示。

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills