gabrieldabbahSkillgabrieldabbah/genesis/skills/security-audit/SKILL.md
Audit a surface for security problems, score them honestly, and turn each into a task with a fix. Use before declaring work done, after wiring an integration, before a deploy handoff, or when the user says \"/security-audit\", \"check security\", \"audit this\", \"is this safe\". Builds the checklist from general application-security concerns plus the per-integration items in the integrations registry. Reports findings with severity, file:line and evidence; states which fixes it applied and which need a human decision; never prints secrets.
gonimarSkillgonimar/claude-web-studio/skills/security-audit/SKILL.md
Audits the application against OWASP Top 10:2025 / ASVS for the project's stack — code review by appsec-engineer, tooling (vulnerability, secret and SAST scanners), CVSS-scored findings with fixes in docs/security/security-audit-<date>.md; modes full, quick, api, auth, infra, <path>. Required before release; use for 'security audit', 'is this secure', 'OWASP check', 'review the auth code'.
jLAM-ERRSkilljLAM-ERR/corp-llm-gateway/.claude/skills/security-audit/SKILL.md
Whole-repo leak-surface security audit of corp-llm-gateway against its zero-leak criterion and the 6 CLAUDE.md invariants — sanitizer coverage, NEVER-gate, auth/tokens, placeholder bijection, egress/DLP. Produces CONFIRMED/SUSPECTED findings with file:line + fixes. Use for "security audit", "sec-audit", "find leak paths", "do the invariants still hold". For reviewing a pending diff instead, use the built-in security-review.
kelgirechandrakant-cpuSkillkelgirechandrakant-cpu/vibe-coding-playbook/skills/security-audit/SKILL.md
Security audit methodology. OWASP Top 10 + STRIDE threat model with zero-noise false positive filtering. Checks API key exposure, database rules, XSS vectors, CSRF, auth bypass. Use when handling user data or preparing for production.
KirillTrubitsynSkillKirillTrubitsyn/kirilltrubitsyn-claude-skills/.claude/skills/security-audit/SKILL.md
Комплексный аудит безопасности приложений, API, репозиториев, AI/agent-систем, MCP-интеграций, инфраструктуры и цепочки поставок. Использовать при явном запросе — «аудит безопасности», «security audit», «проверь на уязвимости», «security review», «threat model», «hardening», «проверка перед продакшеном», «prompt injection», «MCP security», — а также при secure-design review или планировании авторизованного пентеста. Не использовать для обычного code review, отладки или рефакторинга без запроса о безопасности.
saitarrunSkillsaitarrun/Devforge-ai/skills/security-audit/SKILL.md
This skill should be used when the user mentions keywords related to security-audit.
senoritadeveloper01Skillsenoritadeveloper01/claude-skills/.claude/skills/spring-security/SKILL.md
Use this skill when implementing or reviewing security in a Spring Boot application. Covers authentication, authorization, input validation, secure configuration, and API security best practices.
Wang200935SkillWang200935/security-agent-skills/skills/cloud-security/security-audit/SKILL.md
Security audit of a codebase — web apps, APIs, services, CLI tools, libraries,
xsourabhsharmaSkillxsourabhsharma/ai-security-audit-pro/skills/security-audit/SKILL.md
Defensive web and web-application security auditing for local projects, localhost, staging, and authorized public/private websites. Use when the user asks to audit, scan, review, find vulnerabilities, check OWASP issues, inspect security headers, assess APIs, or produce a security report for a website or web app.
thejefflarsonSkillthejefflarson/soundcheck/.claude/skills/security-review/SKILL.md
Runs a full OWASP/CWE security audit via isolated subagents. Use when the user
AndrewDrygaSkillAndrewDryga/emisar/.claude/skills/security-engineer/SKILL.md
Put on the security-engineer hat for emisar — threat-model and harden anything touching auth, runner trust, MCP, policies, approvals, audit, or untrusted input. Use when reviewing or building auth/session/MFA, the runner socket, the MCP API, policy evaluation, approval flows, audit logging, secret handling, or any code that ingests runner/LLM input. emisar IS a security product — this hat is mandatory there.
NoorQureshiSkillNoorQureshi/ronin/skills/ai-ml/ai-mcp-security/SKILL.md
Assess Model Context Protocol (MCP) servers and agent tool integrations — tool poisoning, prompt injection via tool descriptions/results, over-broad scopes, and unauth tool exposure. Load when the target uses MCP servers, agent tool/function integrations, or connectors. Signals: mcp.json, MCP server, tool schemas, connector marketplace, agent with external tools.
caiaffaSkillcaiaffa/claude-code-ultimate-engineering-system/skills/security-review/SKILL.md
Review code, APIs, infrastructure, IAM, secrets, and data handling for practical application and platform security risks.
yusupsupriyadiSkillyusupsupriyadi/claude-code-mastering/.claude/skills/security-review/SKILL.md
Performs comprehensive security review of code changes. Automatically activates when reviewing authentication, authorization, data handling, input validation, encryption, or when user mentions security audit, vulnerability, or penetration testing. Keywords: security, auth, authentication, authorization, jwt, token, vulnerability, injection, xss, csrf, owasp
alexpateSkillalexpate/devtool-skills/skills/security-page/SKILL.md
Build a credible security/trust page for a developer tool before SOC 2 — concrete controls, encryption specifics, subprocessor list, responsible disclosure, data lifecycle, and honest scoping of what you can claim. Use when the user wants a security page, trust page, or trust center, asks "do we need SOC 2", got a vendor security questionnaire, or is losing deals to security review. Also use when they mention a DPA, subprocessors, security.txt, responsible disclosure, or "enterprise readiness", even if they never say "security page".
BobagiSkillBobagi/claude-skills/security-sweep/SKILL.md
Varredura de segurança agnóstica a projeto que ENCONTRA, TESTA ao vivo (adversarialmente) e CORRIGE vulnerabilidades — não só reporta. Cobre race conditions/TOCTOU, IDOR/autorização, enumeração de usuário, injeção (SQL/command), SSRF, upload, XSS, segredos, sessão/auth, crypto, exposição de dados e lógica de negócio, contra uma rubric versionada que cresce a cada uso. Use quando o usuário pedir "varredura de segurança", "faça um pentest", "está seguro?", "audite a segurança", "verifique vulnerabilidades", ou ao final de QUALQUER feature que toque autenticação, dinheiro, permissões, input do usuário, upload ou dados sensíveis.
bt2goSkillbt2go/claude-skills/skills/security-pass/SKILL.md
Use when the user wants a security check of a diff, an endpoint, or code handling input, auth or secrets.
Shobhit-HalseSkillShobhit-Halse/skills/skills/security-expo/SKILL.md
Security and crash-prevention skill for React Native and Expo mobile apps. MUST be loaded when the task touches: auth flows, token handling, login/logout, session management, secure storage, API request construction, deep links, push notification handlers, WebViews, input validation, error handling, crash prevention, error boundaries, secrets, environment variables, certificate pinning, TLS configuration, biometric authentication, rate limiting, brute-force protection, dependency auditing, LLM/AI feature integration, or production hardening. Also load when reviewing AI-generated code that touches networking, storage, or auth. This skill exists because mobile clients are untrusted devices and the backend is the only trust boundary — do not skip loading it because the task "looks small". Version 1.1.0.
Yakoub-aiAGENTS.mdYakoub-ai/Tech-Skills/skills/security/AGENTS.md
Coordinates security and compliance - manages Security Architects, Compliance Officers, and Security Hardeners
CapristaSkillCaprista/KarvyLoop/.claude/skills/security-review/SKILL.md
Dev-time security audit of KarvyLoop's OWN source (twin of /code-review, but for security). Use when asked to "audit the security of these changes", "审这轮改动的安全", "security review this endpoint/diff", or before landing anything that touches the untrusted-input frontier (new API endpoints, URL/file fetch, tool authorization, sandbox, LLM output that reaches a persistent store or the shell). Runs a multi-agent adversarial audit — parallel discovery agents, then ≥3 refutation passes per finding (keep only if ≥2/3 say REAL) — and REPORTS ONLY; it never edits code. Not a KarvyLoop product feature.
