菜单
Run a security audit (dependencies, secrets, auth, inputs). Use when the user asks for a security review, dependency audit, or to check for vulnerabilities and hardcoded secrets.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/wchen02/cursor-agent-learning --skill security-audit命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Use a Markdown file in the repo as persisted agent memory across chats. Use when the user wants session-spanning context, a decision log, or to resume work without re-pasting history.
End-to-end project-level vibe workflow with split on-disk state under .cursor/project-vibe-master/ for resume; state template and optional generated data live in this skill (initial-state/, data/). Combines rules, shell/scripts, MCP, hooks, subagents, HITL, and review/deploy skills.
Full agile lifecycle with MCP: use MCP to fetch current docs/API schema during discovery and development. Use when building a project from a rough idea that depends on external APIs or libraries and you want up-to-date references via MCP.
基于 SOC 职业分类
正在显示 SKILL.md
| name | security-audit |
| description | Run a security audit (dependencies, secrets, auth, inputs). Use when the user asks for a security review, dependency audit, or to check for vulnerabilities and hardcoded secrets. |
When the user asks for a security audit or review, follow this workflow.
Ask or infer from the request; if unclear, do a quick check and offer to run a full audit.
npm audit, pip audit, or project-equivalent). List high/critical and suggest upgrades or mitigations.Use the same severity labels and structure as in examples.md so the report is consistent and actionable.