Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Expert SWIFT Customer Security Programme (CSP) advisor covering the Customer Security Controls Framework (CSCF v2026). Use this skill whenever a user asks about SWIFT CSP, CSCF controls, SWIFT security attestation, KYC-SA portal, SWIFT architecture types (A1/A2/A3/A4/B), mandatory vs advisory controls, independent assessment, SWIFT secure zone, secure flow zone, MFA for operators, SWIFT messaging security, payment fraud prevention on SWIFT, gap analysis for CSCF, or compliance with SWIFT's 32 controls (26 mandatory, 6 advisory in v2026) across the three objectives: Secure Your Environment, Know and Limit Access, Detect and Respond. Control 2.4 (Back-Office Data Flow Security) is now mandatory in v2026. v2026 attestation window is July 1– December 31, 2026. Trigger for any SWIFT CSP or CSCF compliance question.
Traces ransomware cryptocurrency payment flows using blockchain analysis tools such as Chainalysis Reactor, WalletExplorer, and blockchain.com APIs, identifying wallet clusters and tracking fund movement through mixers and exchanges to support law enforcement attribution. Use when tracing ransomware bitcoin payments, performing cryptocurrency wallet forensics, or gathering blockchain threat intelligence on extortion payments.
Expert API architect specializing in RESTful API design, GraphQL, gRPC, and API security. Deep expertise in OpenAPI 3.1, authentication patterns (OAuth2, JWT), rate limiting, pagination, and OWASP API Security Top 10. Use when designing scalable APIs, implementing API gateways, or securing API endpoints.
Hunt CORS misconfigurations — origin reflection with credentials, null-origin trust, subdomain-regex bypass (unanchored vs. unescaped dot vs. prefix-only), pre-flight (OPTIONS) gating bypass, and postMessage origin checks. High severity only when an attacker-controlled origin can perform a credentialed cross-origin read of sensitive data and you have proven it in a browser. Use when testing API endpoints, SPAs, or any app emitting Access-Control-* headers.
Hunt source code and build artifact leakage — JavaScript source maps (.js.map) reconstructing TypeScript/ES6 source, Swagger/OpenAPI JSON endpoint discovery, .env/.git exposure, webpack chunks with hardcoded secrets, robots.txt/security.txt recon, build-info files, asset-manifest.json API route discovery, .DS_Store file listing. Use at the START of every recon session — these findings often unlock the entire attack surface.
Upgrade Stellar/Soroban smart contracts using OpenZeppelin's upgradeable module. Use when users need to: (1) make Soroban contracts upgradeable via native WASM replacement, (2) use Upgradeable or UpgradeableMigratable derive macros, (3) implement atomic upgrade-and-migrate patterns with an Upgrader contract, (4) ensure storage key compatibility across upgrades, or (5) test upgrade paths for Soroban contracts.
Audit AI agent configurations for security risks — excessive permissions, prompt injection surfaces, data exfiltration paths, and missing guardrails. Use when reviewing CLAUDE.md files, MCP configs, agent orchestration code, or any AI agent setup
Quét bảo mật mã nguồn bằng Trivy — tự check/cài Trivy nếu chưa có, quét vuln + misconfig + secret trên be/fe, xuất report JSON+HTML, tóm tắt HIGH/CRITICAL, và đề xuất/áp dụng fix (bump deps, USER non-root). NGOÀI quét static Trivy, còn KIỂM CHỨNG ĐỘNG các giả định mặc định hay sai của dev (auth chỉ ở UI, "nội bộ nên an toàn", CORS, config default, lệch branch deploy) bằng request thật. Dùng khi user nói "quét bảo mật", "trivy", "scan vuln", "security scan", "check CVE", "có lỗ hổng không", "an toàn chưa", "/orca-sec-scans".
Guides tenant isolation architecture in Qdrant for multi-tenant or multi-user applications. Use when someone asks how to isolate customer data, build multi-tenant search/RAG, decide how many collections to create, partition tenants by payload, or keep a customer's data in a specific country or region for legal reasons. Also use when one customer's data is much larger than others and slowing everyone down, or one tenant is hogging resources.
Audits the full lifecycle of bearer/API tokens protecting an internet-exposed HTTP API — minting entropy and format, hash-only server storage, transport rules, scoping, expiry and rotation, revocation, per-key rate limits, and log hygiene — with read-only evidence commands and hardened reference implementations.
Query and analyze security events and alerts detected by Alibaba Cloud Firewall IPS (Intrusion Prevention System), helping quickly locate threats and provide remediation recommendations. Triggers when user mentions IPS alerts, intrusion detection, intrusion prevention, attack events, security alerts, threat detection, attack analysis, IDS/IPS, being attacked, any attacks, security incidents, security warnings, server under attack, machine alarms. Also triggers when user asks about "any recent attacks", "which assets were attacked", "does this IP have attack behavior", "security alerts for a specific server/machine", "which IPs attacked a specific IP", even without explicitly saying "IPS".
Hunt gRPC vulnerabilities — server reflection enabled (enumerate all services/methods), missing authentication / metadata-stripping on internal endpoints, plaintext gRPC over HTTP/2, internal endpoint disclosure, proto file leakage, gRPC-Web/grpc-gateway transcoding injection, and HTTP/2 Rapid Reset DoS (CVE-2023-44487). Use when target exposes port 50051 / 443 / 8443 / 9090 with HTTP/2, when grpcurl/grpcui detects reflection, when an Envoy or grpc-gateway proxy is fronting a microservice, or when recon reveals a microservice architecture.
Hunt Node.js specific vulnerabilities — Prototype Pollution → RCE chains (lodash/merge/assign), Express trust proxy misconfiguration, child_process/eval injection, template engine SSTI (EJS/Pug/Handlebars), path traversal in file servers, require() injection, environment variable exfil via /proc/self/environ. Use when target runs Node.js/Express/Fastify/NestJS/Koa.
Hunt session management vulnerabilities — session fixation (no regeneration on login), insufficient invalidation on logout / password-change / email-change, predictable or low-entropy session IDs, JWT-as-session with no exp/revocation, refresh-token rotation/reuse-detection gaps, OAuth/SSO session linkage, device-bound-session (DBSC) downgrade, and cookie attribute issues (Secure/HttpOnly/SameSite/__Host-). Validate with TWO real sessions (attacker A + victim B), body-diff every 200, and OOB confirmation for theft chains. Medium to Critical (fixation→admin hijack, no-invalidation→persistent ATO).
Hunt WebSocket vulnerabilities — Cross-Site WebSocket Hijacking (CSWSH), missing/weak Origin validation on the WS handshake, no per-message authentication, message tampering, socket.io namespace/room authorization bypass, and handshake-layer Upgrade smuggling. Use when target has WebSocket endpoints (ws:// or wss://), socket.io / SignalR / Phoenix Channels, real-time features, chat, live dashboards, notifications, or trading platforms.
Hunt client-side DOM vulnerabilities — DOM Clobbering (overwrite JS globals via HTML injection), PostMessage hijacking (missing origin check), Service Worker abuse (intercept requests from same-origin script), CSS Injection/Exfiltration (attribute selectors → token char-by-char via OOB), client-side template injection, dangerouslySetInnerHTML. Grounded in named public research: Gareth Heyes / PortSwigger DOM-clobbering + DOM-Invader, Michał Bentkowski DOMPurify clobbering bypasses, jQuery htmlPrefilter XSS (CVE-2020-11022 / CVE-2020-11023), d0nut CSS-exfil research. Use when hunting DOM-XSS, client-side auth bypass, or token exfiltration without server-side interaction
Hunt Local File Inclusion (LFI), Remote File Inclusion (RFI), and Path Traversal — /etc/passwd read, log poisoning → RCE, PHP filter-chain RCE (no upload needed), php:// / data:// / zip:// / phar:// wrappers, RFI via allow_url_include, directory traversal read/write/delete. Covers OOB/blind LFI confirmation and false-positive discipline. Use when hunting file-include or path-traversal bugs on any target
Use when generating, refactoring, reviewing, or debugging Make App single-app permission enforcement: /principal/permission, App-scoped IAM matching, permission-aware Schema, entity/field/operation guards, or permission refresh. Triggered by 单应用权限, 权限范围, 字段可新建、可见、可编辑, creatable, createFields, data.record.*, meta.entity.*, meta.field.*, route guards, or URL bypass. Use make-app-actions for selection and batch actions. Does not own platform-admin permissions, auth, generic Service APIs, UI layout, CanvasTable internals, DSL, deployment, or runtime packaging.
Use when the user wants to create a visual code review on a Miro board from a pull/merge request (GitHub, GitLab, or any forge), local uncommitted changes, or a branch comparison. Produces a file-changes table, summary/architecture/security docs, and architecture diagrams, then links them back from the PR/MR.
Step-by-step guide for setting up Better Auth authentication with Convex and TanStack Start. Use this skill when configuring authentication in a Convex + TanStack Start project, troubleshooting auth issues, or implementing sign up/sign in/sign out flows. Covers installation, environment variables, SSR authentication, route handlers, and the expectAuth pattern.
Manage dependencies and supply chain security to prevent vulnerable or malicious packages. Use this skill when you need to audit dependencies, update packages, check for vulnerabilities, understand supply chain attacks, or maintain dependency security. Triggers include "dependencies", "npm audit", "supply chain", "package security", "vulnerability", "npm update", "security audit", "outdated packages".
Hunt Host Header Injection — password reset poisoning → ATO, web cache poisoning via unkeyed Host/X-Forwarded-Host, routing-based SSRF (Host picks upstream → cloud metadata/internal services), path-override SSRF/ACL-bypass (X-Original-URL/X-Rewrite-URL), OAuth redirect_uri/issuer poisoning, and absolute-URL link poisoning in emails. High to Critical when it reaches ATO or mass cache poisoning. Built on public Host-header research (PortSwigger 'Practical web cache poisoning' + James Kettle, and the classic password-reset-poisoning class). Use on any forgot-password flow, CDN/reverse-proxy-fronted app, OAuth/OIDC endpoint, or absolute-URL-in-email feature
Hunt TLS/SSL and DNS misconfigurations — missing HSTS (downgrade attack), weak cipher suites, expired/invalid certificates, mTLS bypass, missing SPF/DKIM/DMARC (email spoofing), DNS Zone Transfer (AXFR), dangling CNAME subdomain takeover, CAA records. Most of these are Info/Low on their own — this skill is opinionated about which findings actually pay (spoofable DMARC with delivered-to-inbox proof, AXFR returning internal hosts, dangling-CNAME takeover) versus which get rejected as best-practice noise (missing CAA, missing HSTS with no MitM position). Use during recon to find infrastructure weaknesses, and to TRIAGE them honestly before reporting
Expert in Cilium eBPF-based networking and security for Kubernetes. Use for CNI setup, network policies (L3/L4/L7), service mesh, Hubble observability, zero-trust security, and cluster-wide network troubleshooting. Specializes in high-performance, secure cluster networking.
Hunt Kubernetes & Docker — API anonymous access, kubelet 10250 exec (SPDY/WebSocket, NOT plain POST) and the simpler /run primitive, etcd 2379 unauth, dashboard skip-login, RBAC misconfig, secret/SA-token abuse, docker.sock host escape, runc/container-escape (Leaky Vessels CVE-2024-21626), API-server-mediated nodes/proxy RCE, EphemeralContainers node-shell, bound/projected SA-token audience+expiry abuse, admission-controller bypass, Helm/Tiller remnants. Use when target runs containerized infra, exposes K8s ports (6443/10250/10255/2379/8443), or cloud metadata reveals K8s service accounts.
Establish a security baseline for a website or web app. Use when configuring HTTPS and TLS, setting security headers, planning secrets management, evaluating CSP policies, conducting a basic security audit, or hardening a site before launch. Triggers on security headers, HTTPS, TLS, CSP, content security policy, HSTS, secrets management, vulnerability scans, security audits, hardening, OWASP, and security baselines. Also use when a security review is required for compliance or before going live.
Implements secure authentication patterns including login/registration, session management, JWT tokens, password hashing, cookie settings, and CSRF protection. Provides auth routes, middleware, security configurations, and threat model documentation. Use when building "authentication", "login system", "JWT auth", or "session management".
Hunt Laravel specific vulnerabilities — Debug mode leakage (APP_DEBUG=true exposes full stack trace + env vars), Laravel Telescope/Horizon dashboard unauthorized access, Ignition RCE (CVE-2021-3129), Signed URL manipulation, Queue Worker abuse, mass assignment via Eloquent, deserialization via cookies, .env file exposure. Use when target runs Laravel (PHP) — detected via X-Powered-By, Laravel session cookies, or /storage/ paths.
Audits project dependencies for outdated packages, duplicates, heavy/problematic libraries, security vulnerabilities, and risky version combinations. Generates prioritized reports with security, performance, and maintainability insights, upgrade paths, and safe pinning recommendations. Use when users request dependency audits, package updates, security checks, or dependency optimization.
Compares two face images 1:1 using Didit's standalone Face Match API (POST /v3/face-match/). Use to check whether a selfie matches an ID document portrait or previously enrolled photo, verify that two photos show the same person, or add selfie-to-document biometric comparison. Returns a 0–100 similarity score and an Approved/Declined status against a configurable decline threshold (default 30), with optional image rotation. Does not enroll faces or run blocklist or duplicate checks.
Hunt for Spring Boot-specific vulnerabilities: Actuator endpoints (heapdump, env, loggers, mappings, shutdown), Spring Expression Language (SpEL) injection → RCE, H2 console RCE, Jolokia JMX exposure, Spring4Shell (CVE-2022-22965), Spring Cloud Function SpEL (CVE-2022-22963), and credential extraction from heap dumps. Use when the target runs Spring Boot, detected via the X-Application-Context header, /actuator, Whitelabel Error Page, or Java stack traces.
Tests web application URL parameters for Server-Side Request Forgery by probing cloud metadata endpoints (AWS/GCP/Azure at 169.254.169.254), internal network services, and protocol handlers (file://, gopher://, dict://) using a Python script, including IP-encoding bypass and DNS rebinding checks. Use during authorized penetration testing to confirm SSRF in a URL-fetching parameter and generate a vulnerability report
Hunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable
IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida_* modules (50+), idautils iterators, and common patterns.
Implements secure JWT (RFC 7519) signing and verification using HMAC-SHA256, RSA-PSS, ES256, and EdDSA, including token expiration, claims validation, and defenses against algorithm-confusion, none-algorithm, and key-injection attacks. Use when adding or hardening JWT-based authentication/authorization, or auditing token verification code for common JWT vulnerabilities
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.