Expert security architect providing comprehensive security guidance, architecture assessments, threat modeling, and compliance verification. Follows OWASP, NIS2, ISO 27001, NIST, and industry best practices. Use for security architecture design and review, threat modeling, security strategy, compliance assessment (OWASP, NIS2, GDPR, PCI DSS, SOC 2), infrastructure security, API security patterns, and incident response planning. For code-level security reviews, use the code-review skill.
Systematyczny audyt bezpieczeństwa dla React 19 + Supabase + Edge Functions. Używaj przy review bezpieczeństwa, przed deployem, przy pracy z auth/authz, walidacją inputów, RLS policies, XSS, OWASP Top 10.
Security review for code, APIs, and system designs. Always use this skill when reviewing code for vulnerabilities, auditing authentication or authorization, evaluating input handling, checking for secrets or hardcoded credentials, reviewing dependencies, or threat modeling. Use when the user says "is this secure", "review this for security issues", "could this be exploited", "check for vulnerabilities", "threat model this", "review for SQL injection", "is this JWT implementation safe", or "is my auth correct". Also use proactively when implementing auth, handling untrusted input, or storing sensitive data.
Security rules for projects following the air-gapped, declarative-first architecture. Covers Content Security Policy, recommended security headers, and the architectural decisions that enable a strict CSP without unsafe-inline or unsafe-eval. Use when configuring deployment, reviewing CSP, or auditing for inline-script or inline-style violations.
Segurança de aplicações production-grade: OWASP Top 10, autenticação/autorização, gestão de segredos, threat modeling (STRIDE), validação de input e secure defaults. Use quando o usuário mencionar: "segurança", "vulnerabilidade", "OWASP", "autenticação", "autorização", "SQL injection", "XSS", "CSRF", "segredos", "threat model", "é seguro?", "hardening", "pentest". Não auxilia ataques maliciosos — foco em defesa e testes autorizados.
Route Keychain Services implementation tasks to the correct Knowledge Contracts -- item CRUD via SecItemAdd/SecItemCopyMatching/SecItemUpdate/SecItemDelete, accessibility levels, access groups and sharing, and storing structured/Codable data. Use when working with kSecClassGenericPassword, kSecClassInternetPassword, OSStatus, errSecSuccess, errSecItemNotFound, errSecDuplicateItem, kSecAttrAccessible, kSecAttrAccessGroup, Keychain Sharing, or kSecValueData. v1 is general (non-biometric-bound) Keychain item CRUD for generic/internet password items -- no SecAccessControl/biometric binding, no AutoFill/credential providers, no iCloud Keychain sync, no certificate/key/identity item classes. Triggers on SecItemAdd, SecItemCopyMatching, SecItemUpdate, SecItemDelete, kSecClassGenericPassword, kSecClassInternetPassword, kSecAttrAccessible, kSecAttrAccessGroup, Keychain access group, kSecValueData, Keychain, credential storage.
Security Category — Ship Score Sub-Skill
You are running the **Security** category of a Ship Score production readiness audit.
Follow every instruction below precisely. Do not add checks beyond
Audit security boundaries in AI, agent, RAG, and MCP systems, or manage project secrets with SOPS and age. Use for threat models, scoped security reviews, encrypted dotenv migration, recipient rotation, and secret exposure response.
Audit de sécurité rapide pour projet PHP/Symfony. Analyse les fichiers modifiés ou un périmètre donné. Détecte injections SQL, XSS, CSRF, exposition de données, permissions manquantes. Basé sur OWASP Top 10. Utiliser avant un commit ou pour auditer un périmètre.
Audita e projeta a segurança de aplicações: autenticação e sessão (OAuth com PKCE, OIDC, JWT), autorização por recurso (RBAC/ABAC, BOLA/IDOR), entrada e injeções, criptografia e segredos, dependências, cabeçalhos web, logs e privacidade, com checklist baseado no OWASP, achados com severidade e plano de remediação. Use sempre que o usuário pedir 'audite a segurança', 'isto é seguro?', 'revise a autenticação', 'proteja este endpoint', 'vazou um segredo', 'vulnerabilidades', 'OWASP', 'hash de senha', 'CSP' ou 'permissões', mesmo sem a palavra 'segurança'. NÃO use para desenhar contratos de API (isso é -api-design), infraestrutura e pipelines (isso é -devops) nem para revisar um diff em geral (isso é -code-review).
Secure web and desktop application development. Use when writing authentication, authorization, API endpoints, form handling, database queries, file uploads, Electron apps, Tauri apps, IPC handlers, cryptography, secrets management, security headers, input validation, or when reviewing code for vulnerabilities. Covers OWASP Top 10, XSS, CSRF, SQL injection, SSRF, command injection, path traversal, and desktop app security.
Security audits and threat modeling — find and reason about vulnerabilities in auth, input handling, data access, secrets, and dependencies. Use when reviewing code for security, threat-modeling a feature, hardening an endpoint, handling auth/authz, or checking for injection, secret leakage, or unsafe data exposure. For a focused review of the current diff, prefer the `/security-review` command.
Application security standards and hardening practices. Use when: reviewing code for vulnerabilities, implementing authentication, configuring CORS, adding input validation, managing secrets, scanning dependencies, setting CSP headers, reviewing IAM policies, auditing an existing application for OWASP top 10 vulnerabilities, or hardening an existing deployment. Covers OWASP top 10, secrets management, dependency auditing, and security headers.
The security role — the member who owns the team's application-security evidence (threat models, authorized scans, validated findings, private disclosure, the smallest defensible fix, and honest posture claims). Use when threat-modeling a system or a change, reviewing code or a workflow for security, running or reading a scanner, judging whether a finding is real and how severe, handling a leaked secret, reviewing a new dependency or the release pipeline, or writing anything public about security.
Loaded automatically by execute-task and verify-task when changes touch auth, billing, migration, tenant isolation, infra, or shared contracts - security checklist. Do not invoke standalone unless the user specifically asks for a security review
安全审计与加固。覆盖SAST/SCA/密钥扫描/STRIDE威胁建模/合规检查，按语言特定工具链识别漏洞并提供修复方案。Use when the user asks to check security, scan for vulnerabilities, audit code, or prepare for compliance.
Router for application and code security — scanning a repository or diff for vulnerabilities, reviewing auth, secrets, and injection risks, generating patches for findings, and running a security pass before shipping. Use when the user mentions a security scan, vulnerability audit, CVE, secrets in code, auth review, injection, XSS, SQL injection, SSRF, dependency risk, or asks to check whether their code is safe to ship.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
tomas-uSkill
