Security
Security agent skills give AI agents disciplined security workflows: code review for vulnerabilities, secret handling, dependency audits, and hardening checklists. Every skill on SkillMD also passes its own safety review before listing, with capability flags shown on each page.
-
majiayu000 Bundle Cipher Sigma<!-- Copyright (c) 2026 defconxt. All rights reserved. -->
567 -
majiayu000 Bundle Clawsec FeedSecurity advisory feed with automated NVD CVE polling for OpenClaw-related vulnerabilities. Updated daily.
567 -
majiayu000 Bundle ClawtributorCommunity incident reporting for AI agents. Contribute to collective security by reporting threats.
567 -
majiayu000 Bundle Convex AuditAudit a Convex-backed codebase for schema quality, security, runtime boundaries, migrations, and function-surface risks. Use when the user asks for a Convex review, backend audit, contract analysis, or remediation plan. Do not use for green-field feature-spec generation; use convex-feature-spec for that.
567 -
majiayu000 Bundle Domain SkillUse this template for domain-specific security testing (cryptographic testing, web security methodologies, etc.).
567 -
majiayu000 Bundle Export OscalExport NIST OSCAL (Open Security Controls Assessment Language) JSON from compliance
567 -
majiayu000 Bundle GuardFull safety mode: destructive command warnings + directory-scoped edits. Combines /careful (warns before rm -rf, DROP TABLE, force-push, etc.) with /freeze (blocks edits outside a specified directory). Use for maximum safety when touching prod or debugging live systems. Use when asked to "guard mode", "full safety", "lock it down", or "maximum safety".
567 -
majiayu000 Bundle Hunt SessionHunt Session Management vulnerabilities — session fixation, session prediction (low entropy), insufficient invalidation on logout/password change, concurrent session abuse, JWT as session without expiry or revocation, cookie attribute issues (Secure/HttpOnly/SameSite missing). Medium to High impact.
567 -
majiayu000 Bundle Ioc AnalysisAnalyzes indicators of compromise (IOCs) to detect and respond to cybersecurity threats.
567 -
majiayu000 Bundle IOS Add AuthAdd authentication to an iOS app with Sign in with Apple, biometrics, and Keychain storage.
567 -
majiayu000 Bundle Laravel AuthUse when implementing user authentication, API tokens, social login, or authorization. Covers Sanctum, Passport, Socialite, Fortify, policies, and gates for Laravel 12.
567 -
majiayu000 Bundle Npmrc ConfigNPM registry configuration template (.npmrc.template) and validation logic for GitHub Packages authentication with pnpm hoisting settings. Includes 4 critical standards (GitHub Package Registry config with token placeholder, pnpm hoisting for monorepo compatibility, exact version management, security documentation). Use when creating or auditing .npmrc.template files to prevent token leakage.
567 -
majiayu000 Bundle Oauth2 FlowsOAuth 2.0認可フローの実装パターンとセキュリティベストプラクティス。 Authorization Code Flow、PKCE、Refresh Token Flowの正確な実装を提供。 Web/SPA/モバイルアプリでの安全な認可フロー実装を支援。 Anchors: • OAuth 2.0 Simplified (Aaron Parecki) / 適用: 認可フロー全般 / 目的: RFC準拠の正確な実装 • Web Application Security (Andrew Hoffman) / 適用: セキュリティ設計 / 目的: 脅威モデリングと対策 • RFC 6749 (OAuth 2.0 Framework) / 適用: プロトコル仕様 / 目的: 標準準拠の担保 Trigger: Use when implementing OAuth 2.0 authentication, configuring authorization flows, integrating with OAuth providers, implementing PKCE for SPAs, or managing token lifecycle. oauth2, authorization code, pkce, access token, refresh token, oauth provider, google auth, github oauth
567 -
majiayu000 Bundle Pass Secrets使用 Pass (Password Store) 统一管理所有 API 密钥和敏感凭证。Pass 基于 GPG 加密,支持 Git 同步,安全可靠。
567 -
majiayu000 Bundle Pivot On IocExplore GTI relationships for an IOC to discover related entities. Use to expand investigation by finding connected domains, IPs, files, or threat actors. Takes an IOC and relationship types to query.
567 -
majiayu000 Bundle Script AuditAudit third-party scripts on the storefront for performance and security impact
567 -
majiayu000 Bundle Secrets SyncTwo-way secret synchronization between master vault and projects. Detects new secrets, namespaces by project, and handles SOPS re-encryption. Use when user says 'sync secrets', 'pull secrets', 'push secrets', or 'secrets diff'.
567 -
majiayu000 Bundle Semgrep ScanRun Semgrep SAST analysis for security and code quality
567 -
majiayu000 Bundle Sops Add KeyAdd a new machine's age public key to .sops.yaml and re-encrypt all files. Use for multi-machine setups. Use when user mentions "add key", "add machine", "sops add key", "new machine", "authorize machine", "share key", "add public key", "multi machine sops".
567 -
majiayu000 Bundle Sops DecryptDecrypt SOPS-encrypted YAML files back to .env format. Finds *.enc.yaml files, decrypts, and converts YAML back to dotenv. Use when user mentions "decrypt env", "sops decrypt", "decrypt secrets", "restore env", "decrypt .env", "restore secrets", "decrypt environment files".
567 -
majiayu000 Bundle Sops EncryptEncrypt .env files using SOPS + age. Converts dotenv to YAML format (avoids SOPS bug #1435), then encrypts. Auto-detects unencrypted .env files. Use when user mentions "encrypt env", "sops encrypt", "encrypt secrets", "encrypt .env", "encrypt environment", "re-encrypt", "update encrypted".
567 -
majiayu000 Bundle Suede SignupSuede-owned signup conversion discipline. Use when auditing or redesigning account creation, registration, or trial-start flows, including field friction, progressive profiling, identity options, mobile behavior, abandonment, and measurement. NOT FOR: post-signup activation (use suede-onboarding), lead-capture forms (use suede-site-alchemy), or deploying auth and compliance changes without review.
567 -
majiayu000 Bundle Triage AlertTriage a security alert or case. Use when given an ALERT_ID or CASE_ID to assess if it's a real threat. Enriches IOCs, searches SIEM for context, and determines if the alert should be closed (false positive) or escalated for investigation.
567 -
majiayu000 Bundle Woo SecurityImplement WooCommerce security — nonces, capabilities, input sanitization, output escaping, data validation, PCI compliance considerations, and WordPress security best practices. Use when hardening a WooCommerce store or reviewing security posture.
567 -
majiayu000 Bundle Ce Test AuditAudit existing tests for ADR-030 anti-patterns, redundancy risk, and compliance with repository test standards.
567 -
majiayu000 Bundle Py Test SwarmOrchestrate hierarchical BioETL test swarms (L1/L2/L3) for full_audit, fix_failures, coverage_boost, optimize, and flakiness_scan with workload-based delegation, telemetry aggregation, flaky analysis, and final reporting in reports/test-swarm/task-id/FINAL-REPORT.md. Use when users request broad test campaigns, failure triage at scale, coverage expansion, or stability diagnostics across layers/providers.
567 -
majiayu000 Bundle Kill ArgumentTwo-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.
567 -
majiayu000 Bundle API DocumentationUse when API code changes (routes, endpoints, schemas). Enforces Swagger/OpenAPI sync. Pauses work if documentation has drifted, triggering documentation-audit skill.
567 -
majiayu000 Bundle Audit CoordinatorOrchestrates comprehensive audits of Claude Code customizations using specialized auditors. Use when auditing multiple components, asking about naming/organization best practices, or needing thorough validation before deployment.
567 -
majiayu000 Bundle Audit PerformanceRun a single-session performance audit on the codebase
567 -
majiayu000 Bundle Audit PermissionsThis skill should be used when the user asks to "audit claude permissions", "audit permissions", "review local claude settings", "promote permissions to global", "clean up claude settings", "find permission patterns", or wants to identify project-local Claude Code permissions that should be added to global configuration.
567 -
majiayu000 Bundle Backend SafeguardSupabase schema validation, RLS enforcement, and API security best practices.
567 -
majiayu000 Bundle Chezmoi WorkflowsDotfile backup and sync with chezmoi. TRIGGERS - chezmoi, dotfiles, sync dotfiles, backup configs, cross-machine sync.
567 -
majiayu000 Bundle Codex Peer Review[CLAUDE CODE ONLY] Leverage Codex CLI for AI peer review, second opinions on architecture and design decisions, cross-validation of implementations, security analysis, and alternative approach generat
567 -
majiayu000 Bundle Configuring NginxConfigure nginx for static sites, reverse proxying, load balancing, SSL/TLS termination, caching, and performance tuning. When setting up web servers, application proxies, or load balancers, this skill provides production-ready patterns with modern security best practices for TLS 1.3, rate limiting, and security headers.
567 -
majiayu000 Bundle Device InspectionExecute comprehensive L1-L4 network device inspection. Use when user asks to "inspect all devices", "run comprehensive health check", "full network audit", or needs systematic L1-L4 analysis across multiple devices.
567
Frequently asked questions
What are Security agent skills?
Security agent skills give AI agents disciplined security workflows: code review for vulnerabilities, secret handling, dependency audits, and hardening checklists. Every skill on SkillMD also passes its own safety review before listing, with capability flags shown on each page.
Which Security skills are most installed?
Popular Security skills on SkillMD right now include kill-argument, cipher-sigma, clawsec-feed. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Security skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.