Best Security Skills

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

Build a `BaseTool[InSchema, OutSchema]` subclass — input/output schemas, `BaseToolConfig`, `run()` (and optional `run_async()`), env-driven secrets, typed failure outputs. Use when the user asks to "add a tool", "create a tool", "wrap an API as a tool", "build a `BaseTool`", "make a calculator/searc

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.

Security scanner for AI agents, MCP servers and agent skills.

Security Scanner for Agent Skills

Guide for designing GraphQL schemas following industry best practices. Use this skill when: (1) designing a new GraphQL schema or API, (2) reviewing existing schema for improvements, (3) deciding on type structures or nullability, (4) implementing pagination or error patterns, (5) ensuring security

A Claude Skill to assist with family history and genealogy research planning.

Use these skills when you need to manage user roles, inspect permissions, and verify security-related configuration parameters.

Run a 42Crunch API Security Audit and fix SQG-blocking issues in an OpenAPI Specification file. Use this skill whenever the user wants to audit an OAS file for security issues, fix SQG-blocking issues, score an API, apply data dictionary enrichment, or remediate audit findings. Triggers on phrases l

Acquire an authenticated session THROUGH MFA/OTP on an in-scope target and emit a reusable session artifact (Playwright storageState + Bearer) so executors can test the post-auth attack surface. Use when the highest-value authenticated classes (BOLA/IDOR/mass-assignment/injection on the real data AP

List, count, summarize, or triage security issues from the Aikido security feed. Use when the user asks about Aikido findings, vulnerabilities, leaked secrets, SAST/IaC/SCA results, cloud or container security issues, or EOL/license/malware alerts surfaced by Aikido.

Reference skill for Zoom authentication. Use after routing to an auth workflow when choosing app credentials, grant types, scopes, token refresh behavior, or debugging Zoom OAuth failures.

OAuth 2.0 and OpenID Connect protocol fundamentals including authorization code flow with PKCE, client credentials, refresh tokens, discovery documents, JWKS, and token introspection. Protocol-level troubleshooting and compliance.

Runs an Aikido security scan on generated, added, or modified code files to detect SAST vulnerabilities and exposed secrets. Use when the user wants to scan code for security issues, after writing or modifying code, or when they mention Aikido, security scan, or SAST. Always run an Aikido scan after

Run authorized repository security scans for vulnerabilities, dependency risk, secrets, and binary policy. Triggers: "security", "run repository security scans for", "security skill".

Fix failing Vanta compliance tests using code. Apply when the user mentions Vanta tests, compliance test failures, remediation, test IDs (e.g., "cloudtrail-log-file-validation"), Vanta URLs (app.vanta.com), or compliance frameworks (SOC 2, ISO 27001, HIPAA).

Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: "production checklist", "harden agent", "production ready", "secure agent", "inboun

Secure authentication implementation patterns. Use when implementing user login, registration, password reset, session management, JWT authentication, OAuth, MFA, or passkeys. Provides production-ready patterns aligned with NIST SP 800-63B-4, OWASP 2026 cheat sheets, OAuth 2.1, and WebAuthn L3, with

Protecting APIs with Duende IdentityServer: JWT bearer authentication, reference token introspection, scope-based authorization, DPoP/mTLS proof-of-possession validation, local API authentication, and multi-audience scenarios.

Retrieve CVE risk scores from NVD. Auto-invoked whenever a CVE ID is mentioned to display CVSS score, severity, CWE, and description.

Offensive testing of perimeter network appliances and VPN crypto — IKE/IPsec (aggressive-mode, transform/DH enum, NAT-T), Check Point SIC/OPSEC, safe firmware/patch-level inference for FortiGate/PAN-OS/Cisco ASA/Citrix feeding CVE applicability, NTLM Type-2 target-info decode, handshake-completion T

Handle blocked destructive commands and configure agent safety guardrails. Triggers: "dcg", "handle a DCG block", "configure agent safety guardrails".

Configure the GrowthBook plugin's API credentials so every other skill can run. Use when the user says "set up growthbook", "configure my api key", "growthbook isn't working", "where do I put my key", or when another skill emits an error pointing here ("GB_API_KEY is not set", "authentication failed

Evaluates FiftyOne plugins for quality, security, and agent-readiness. Use when reviewing a plugin before installation, auditing an existing plugin, validating a plugin you just built, or assessing community plugins for safety. Produces a structured report with scores and actionable recommendations.

DAST-first NightVision scan for an app you just built or changed. Use when a user (or an org CLAUDE.md rule) wants a local, private, staging, or internal web app/API security-scanned. Drives the NightVision MCP `run-app-security-scan` harness.

Guide for agents to help users interpret and act on NightVision DAST scan results. Use when reading SARIF/CSV findings, explaining vulnerabilities, locating vulnerable code, validating findings with curl, prioritizing by severity, suggesting remediations, or marking false positives.

Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and supply chain attacks. Integrates with pentest workflows to discover and exploit AI-specific threats.

Run OWASP LLM Top 10 security assessments against live Agentforce agents. TRIGGER when: user asks for security testing, OWASP scan, red-teaming, penetration testing, security grade, vulnerability assessment, prompt injection test, data leakage test, excessive agency test, security posture check, or

Run an AWS Security Agent threat model review on spec/design documents. Use when the user asks to review a spec for security, run a threat model, check if a design introduces security risks, review requirements.md or design.md for security posture changes, or STRIDE analysis.