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 Bugcrowd Reporting 2Write Bugcrowd-format reports — VRT (Vulnerability Rating Taxonomy) mapping, P1-P5 severity, impact-led writing, and Bugcrowd-specific submission etiquette. Use AFTER triage-validation passes for Bugcrowd programs.
567 - majiayu000 Bundle Dependency Management 2
This skill should be used when managing project dependencies including safe updates, security audits, and compatibility analysis.
567 - majiayu000 Bundle Deps 4
Audit and upgrade project dependencies — check for vulnerabilities and outdated packages
567 - majiayu000 Bundle Middleware Protection 2
Route protection and authorization patterns for Clerk middleware. Use when implementing route guards, protecting API routes, configuring middleware matchers, setting up role-based access control, creating auth boundaries, or when user mentions middleware, route protection, auth guards, protected routes, public routes, matcher patterns, or authorization middleware.
567 - majiayu000 Bundle Security Review 5
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
567 - majiayu000 Bundle Supply Chain Security 3
Software supply chain security guidance covering SBOM generation, SLSA framework, dependency scanning, SCA tools, and protection against supply chain attacks like dependency confusion and typosquatting.
567 - majiayu000 Bundle API Design 9
Design and review REST/GraphQL APIs for correctness, consistency, and security. Generates OpenAPI specs, validates endpoint design, and checks for common API pitfalls.
567 - majiayu000 Bundle Code Quality Review 2
Systematic code review patterns, quality dimensions, anti-pattern detection, and constructive feedback techniques. Use when reviewing code changes, assessing codebase quality, identifying technical debt, or mentoring through reviews. Covers correctness, design, security, performance, and maintainability.
567 - majiayu000 Bundle Integrity Forensics 2
Run the Anti-Autoresearch integrity-forensics DETERMINISTIC slice (numeric core + rules-only adjudicator) against a paper via a SHA-pinned thin launcher, then convert the verdict into a typed policy gate (BLOCK/WARN/NO_NEW_BLOCKER) and an append-only obligations ledger. Codex-native limitation: upstream ships no Codex-native auditor pack, so the full nine-dimension semantic sweep requires a Claude Code session — this pack runs the honestly-scoped deterministic-only mode (it can flag, it can never say CLEAN). Use when user says "integrity forensics", "forensic audit this paper", "投稿前自查诚信".
567 - majiayu000 Bundle Reproducibility Audit 2
Verify that results, builds, and experiments can be reproduced consistently with documented steps and deterministic inputs.
567 - majiayu000 Bundle Audit 5
Audit existing project documentation for quality, completeness, consistency, and code alignment. Scans docs against the actual codebase to find stale references, missing coverage, internal contradictions, and quality issues. Generates a structured findings report with severity levels and actionable fix recommendations. Works on any project with a docs/ directory.
567 - majiayu000 Bundle AI Analyze Permissions
Use when Claude Code permissions have accumulated in settings.local.json and you want to audit, consolidate, or clean up tool permission patterns.
567 - majiayu000 Bundle Auth Patterns 4
Authentication and authorization patterns — JWT, OAuth 2.0, sessions, RBAC/ABAC, password security, MFA, and vulnerability prevention. Use when implementing login flows, protecting routes, managing tokens, or auditing auth security.
567 - majiayu000 Bundle Changelog Quality Pass 2
Use when writing or auditing changelogs and release notes for user-facing, semver-aware clarity. Triggers:
567 - majiayu000 Bundle Security 4
Proactive security engineering for PAI projects. USE WHEN user needs threat modeling, CMMC compliance baseline, security requirements, vulnerability analysis, or security-first design. Prevents security issues during design, not after deployment.
567 - majiayu000 Bundle Security Health Inline 2
Inline orchestration workflow for security vulnerability detection and remediation with Beads integration. Provides step-by-step phases for security-scanner detection, priority-based fixing with vulnerability-fixer, and verification cycles.
567 - majiayu000 Bundle Systematic Code Review 2
4-phase code review: UNDERSTAND, VERIFY, ASSESS risks, DOCUMENT findings.
567 - majiayu000 Bundle Electron UI Patterns 2
ElectronデスクトップアプリケーションのUI実装パターンと設計知識。 BrowserWindow管理、ネイティブUI要素、フレームレスウィンドウを提供。 Anchors: • Electron API / 適用: BrowserWindow・Menu・Tray / 目的: ネイティブUI実装 • Don't Make Me Think / 適用: ウィンドウレイアウト / 目的: ユーザビリティ向上 • Electron Security / 適用: preload・contextIsolation / 目的: セキュアなUI実装 Trigger: Use when configuring BrowserWindow, implementing custom titlebars, designing native menus, developing system tray apps, or building frameless windows. BrowserWindow, Menu, Tray, frameless window, custom titlebar, native UI
567 - majiayu000 Bundle Software Crypto Web3 2
Production-grade blockchain and Web3 development with Solidity (Ethereum/EVM), Rust (Solana), CosmWasm (Cosmos), including smart contract architecture, security patterns, gas optimization, testing strategies, DeFi protocols, and deployment workflows.
567 - majiayu000 Bundle Documenting With Audit 2
Automated documentation auditing - ensures CLAUDE.md coverage, updates stale docs, recommends structural improvements
567 - majiayu000 Bundle Linkedin Profile Optimizer 2
Audit and rewrite a LinkedIn profile end-to-end for 2026: headline, About 7-step, Featured, banner, photo, Experience metrics, Skills, custom URL, recommendations. Triggers on "review my profile", "rewrite my headline", "fix my About", "optimize banner", "profile audit", "LinkedIn bio". Converts resume-style profiles to ones that convert 3-5x better.
567 - majiayu000 Bundle Rust Unsafe Boundary Audit 2
Use when auditing Rust unsafe blocks and FFI boundaries, invariants, tests, and tooling. Triggers:
567 - majiayu000 Bundle Performance Auditing 2
Audit web applications for performance issues and optimize for speed, especially on Cloudflare Workers edge runtime. Use when diagnosing slow pages, optimizing load times, reducing bundle size, improving Core Web Vitals, or optimizing for edge deployment. Triggers on requests like "audit performance", "optimize speed", "improve load time", "reduce bundle size", "Core Web Vitals", or "edge optimization".
567 - majiayu000 Bundle Code Reviewer 5
Provides automated code review capabilities with focus on security, performance, and coding standards.
567 - majiayu000 Bundle Review 14
Review diffs, find mocks, scan bugs, audit code.
567 - majiayu000 Bundle 1password 2
Configure e use a CLI do 1Password (op). Use ao instalar a CLI, habilitar a integração com o app de desktop, fazer login (conta única ou múltipla) ou ler/injetar/executar segredos via op.
567 - majiayu000 Bundle Council 6
Run multi-judge consensus. Use when: an irreversible or high-stakes decision needs independent judges before committing — architecture forks, one-way doors, scoring options.
567 - majiayu000 Bundle OAUTH 2
OAuth 2.0/OIDC flows, provider integration, and token handling.
567 - majiayu000 Bundle Scope 8
Hard-block edits outside declared frozen directories via PreToolUse hook.
567 - majiayu000 Bundle Code Review Checklist 5
Code review criteria covering security, performance, quality standards, and issue prioritization for thorough code analysis.
567 - majiayu000 Bundle Logging Observability 3
Guidelines for structured logging, distributed tracing, and debugging patterns across languages. Covers logging best practices, observability, security considerations, and performance analysis.
567 - majiayu000 Bundle Quality 7
Run a comprehensive code quality review. Checks security, performance, maintainability, project conventions (CLAUDE.md), architecture, and testing. Runs rustfmt and bazel test. Use when user asks for 'review', 'check', 'validate', 'quality', 'lint', or before committing. (project)
567 - majiayu000 Bundle Audit Comprehensive 2
Run all 6 domain audits in parallel and aggregate results
567 - majiayu000 Bundle Continuous Monitoring 2
Set up nightly monitoring of subdomain changes, JS file diffs, new endpoints, and CVE matches against in-scope assets, with Discord/Slack/Telegram notifications. Use when the user has an active engagement and wants to be alerted to new attack surface without manual re-recon.
567 - majiayu000 Bundle Vulnerability Management 3
Vulnerability lifecycle management including CVE tracking, CVSS scoring, risk prioritization, remediation workflows, and coordinated disclosure practices
567 - majiayu000 Bundle 112 Java Maven Plugins 2
Use when you need to add or configure Maven plugins in your pom.xml — including quality tools (enforcer, surefire, failsafe, jacoco, pitest, spotbugs, pmd), security scanning (OWASP), code formatting (Spotless), version management, container image build (Jib), build information tracking, and benchmarking (JMH) — through a consultative, modular step-by-step approach that only adds what you actually need. This should trigger for requests such as Add Maven plugins in pom.xml; Improve Maven plugins in pom.xml. Part of cursor-rules-java project
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 bugcrowd-reporting, dependency-management, deps. 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.