服务上线前的 AI 安全审查，聚焦需要理解代码语义和业务逻辑的安全问题。 覆盖注入防护、认证授权、敏感数据处理、配置安全、业务安全 5 个维度。 适用于 JS/TS 前端、TS/Python 后端项目。 CI/CD 自动化检测（依赖漏洞、敏感信息 grep）不在本 skill 范围内，由流水线承担。 触发词：安全审计、安全检查、上线前检查、有没有漏洞、security audit。 触发场景：release 发版前（强制）、涉及认证/支付/用户数据的改动后（建议）、用户主动要求。
How to install security-audit?
312362115/claude/security-audit
$npx -y skills add 312362115/claude --skill security-auditInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/312362115/claude" --skill "312362115/claude/security-audit"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/312362115/claude" that are relevant to the current task. Run `npx skills add "https://github.com/312362115/claude"` and select the relevant skills, then follow their instructions.
Related
6 picksType
- entra-app-registrationGuides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration.Jul 2026
- azure-complianceRun Azure compliance and security audits with azqr plus Key Vault expiration checks.Jul 2026
- entra-agent-idProvision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token…Jul 2026
- firebase-security-rules-auditorAudits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource…Jul 2026
- golang-securitySecurity best practices and vulnerability prevention for Golang.Jul 2026
- gws-modelarmorGoogle Model Armor: Filter user-generated content for safety.Jul 2026
