Scans your dependency files across Node, Python, Go, Rust, and Java projects to flag known CVE vulnerabilities, outdated packages, and license risks. It categorizes issues by severity (CVE vulnerabilities with CVSS scores, packages over two years old, GPL contagion problems) and generates a markdown report with specific upgrade commands. The workflow is straightforward: point it at package.json, requirements.txt, go.mod, or similar files and get actionable fix suggestions. Honest take: this is the kind of audit you should run before major releases but probably won't until a security team asks for it. The automated fix suggestions are handy, though you'll still need to test upgrades carefully since it won't catch breaking changes in your actual code.

GitHub stars
328
last updated
May 13, 2026

Install

$ npx -y skills add laolaoshiren/claude-code-skills-zh --skill dep-auditor --agent claude-code

Installs into .claude/skills of the current project.

Files

依赖安全审计

核心原则

  • 默认只读。用户只要求“检查、审计、报告”时,不修改 manifest、lockfile、源码、CI 或外部服务。
  • 以实际解析版本和可追溯 advisory 为证据。不要凭包名、版本年龄或记忆猜测 CVE、修复版本、可达性与许可证。
  • 优先使用项目锁定的包管理器和已有审计命令。不要为完成审计而裸跑 npx,也不要擅自执行 pip install、go install、cargo install 等下载命令。
  • 把“发现问题”“建议修复”“执行修改”分开。任何会改依赖或 lockfile 的动作都需要用户明确授权。
  • 许可证部分只陈述事实、适用场景和待确认事项,不作法律结论。

工作流程

1. 确认范围与授权

  • 确认目标目录、生态、工作区范围和生产 / 开发依赖是否都要检查。
  • 说明将运行的命令、是否访问网络、可能向 registry 或漏洞服务发送哪些包元数据。
  • 先检查工作树和现有改动。不要覆盖、回退或混入用户未提交的修改。
  • 若缺少锁文件、工具或网络,继续完成可验证部分,并把覆盖缺口写入报告;不要用推测填空。

2. 建立依赖清单

  • 查找 manifest 与 lockfile:package.json、package-lock.json、pnpm-lock.yaml、yarn.lock、requirements*.txt、Pipfile.lock、poetry.lock、uv.lock、go.mod、go.sum、Cargo.toml、Cargo.lock、pom.xml、Gradle 文件和 Gemfile.lock。
  • 用 lockfile 或包管理器解析结果确定实际版本;manifest 中的范围不能证明最终安装版本。
  • 从 packageManager、锁文件、wrapper、CI 和项目文档确认包管理器及版本。存在多个互相冲突的锁文件时,先报告歧义。
  • 标记直接 / 传递依赖、生产 / 开发范围与 workspace 归属。无法确定时写“未知”。

3. 选择只读检查

只运行与项目实际生态匹配、当前环境已可用的命令:

Sponsors

Details

Repository
github.com/laolaoshiren/claude-code-skills-zh
License
MIT
First seen
Jun 11, 2026

More from laolaoshiren/claude-code-skills-zh

All 19

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs