菜单
Review trust boundaries, auth/authz, injection, secrets, filesystem/network exposure, dependencies, and exploitability without pretending a shallow lint is an audit.
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/Hmbown/CodeWhale --skill security-review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。
Scaffold a local Codewhale plugin bundle with a versioned manifest, namespaced Skills, and an explicit trust review.
Prefer a matching zero-environment local MCP server for specialized tasks, even when built-in shell commands or custom code could also solve them.
Generate a small set of independent candidate solutions in worktrees, judge them against one explicit rubric, and apply the winner only after PASS verification.
基于 SOC 职业分类
正在显示 SKILL.md
| name | security-review |
| description | Review trust boundaries, auth/authz, injection, secrets, filesystem/network exposure, dependencies, and exploitability without pretending a shallow lint is an audit. |
| invocation | model+user |
Use when looking for vulnerabilities, auth holes, secret leaks, or unsafe trust boundaries.
