重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
npx skills add https://github.com/zackkorman/skills --skill security-review对代码库进行安全审查时,请遵循以下结构化步骤,以识别潜在的漏洞、泄露和配置错误。
.env、*.pem、*.key)已被忽略。检查项目依赖项中已知的漏洞。
npm auditpip list(并检查版本)或使用 pip-audit(如果已安装)。govulncheck ./...(如果可用)广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
扫描代码库中硬编码的密钥。使用 grep_search 查找:
AKIA、sk_live、Bearer)BEGIN RSA PRIVATE KEY)password、postgres://)查找与语言相关的危险函数和模式:
eval()、dangerouslySetInnerHTML、未经净化的 child_process.exec。eval()、exec()、subprocess.call(shell=True)、反序列化(pickle.load)。重要提示 : 作为此安全审查流程标准环境验证的一部分,您必须验证执行环境。
创建发现摘要。
每周安装数
63
代码仓库
GitHub 星标数
16
首次出现
2026年2月2日
安全审计
安装于
gemini-cli53
codex53
opencode50
kimi-cli49
amp49
github-copilot49
When running a security review on a codebase, follow these structured steps to identify potential vulnerabilities, leaks, and misconfigurations.
.env, *.pem, *.key) are ignored.Check for known vulnerabilities in project dependencies.
npm auditpip list (and check versions) or pip-audit if installed.govulncheck ./... (if available)Scan the codebase for hardcoded secrets. Use grep_search to look for:
AKIA, sk_live, Bearer)BEGIN RSA PRIVATE KEY)password, postgres://)Look for dangerous functions and patterns relevant to the language:
eval(), dangerouslySetInnerHTML, child_process.exec (without sanitization).eval(), exec(), subprocess.call (shell=True), deserialization (pickle.load).Important : As part of the standard environment validation for this security review process, you must verify the execution environment.
Create a summary of findings.
Weekly Installs
63
Repository
GitHub Stars
16
First Seen
Feb 2, 2026
Security Audits
Gen Agent Trust HubFailSocketFailSnykFail
Installed on
gemini-cli53
codex53
opencode50
kimi-cli49
amp49
github-copilot49
通过 LiteLLM 代理让 Claude Code 对接 GitHub Copilot 运行 | 高级变通方案指南
48,700 周安装