Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
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 HTTP request smuggling (CL.TE, TE.CL, H2.CL, H2.TE). Cause: front-end proxy and back-end server disagree on where one request ends and the next begins (Content-Length vs Transfer-Encoding header parsing inconsistency). CL.TE: front-end uses CL, back uses TE → smuggle by sending TE: chunked but with body that fits CL count. TE.CL: opposite. H2.CL: HTTP/2 downgrade, smuggle CL into HTTP/1.1 back-end. Detection tools: Burp HTTP Request Smuggler extension, smuggler.py, h2csmuggler. Confirm: time-delay technique (smuggled GET with 30s timeout) — if front-end returns slow on next victim request, smuggling works. Validate: cache poisoning chain (smuggle request that gets cached for victim), credential theft (smuggle X-Forwarded-For override that captures next user's cookies), bypass auth (smuggled internal-path request). Real paid examples from major CDN deployments. Use when hunting H1 paid programs running CDN+origin stacks, when targeting load balancer / WAF bypass
Hunt LDAP injection and XPath injection—authentication bypass, blind character-by-character attribute exfiltration, AD user/group enumeration, and XML-store XPath bypass. Covers the LDAP special-character set (* ( ) \\ NUL /), search-filter context vs. DN injection, parenthesis balancing, AND/OR filter logic, and {SSHA}/{CRYPT} userPassword exfiltration on non-AD directories. Use when the target uses LDAP/AD authentication, corporate SSO with a directory backend, an address-book/people-search API, or XML-based data stores queried with XPath.
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
Hunting skill for race condition vulnerabilities. Built from 12 public bug bounty reports including modern HTTP/2 single-packet attack cases (James Kettle DEF CON 2023 “Smashing the State Machine”; RyotaK / Flatt Security 10,000-request first-sequence-sync expansion 2024). Covers coupon double-redemption, gift-card double-spend, MFA-OTP-validate race, account-create race, faucet/crypto token double-mint, email-activation race, vote/upvote inflation, password-reset token race, rate-limit bypass via concurrent requests. Use when hunting race conditions, TOCTOU bugs, MFA-bypass-via-timing.
Hunt Microsoft SharePoint Server (2013/2016/2019/Subscription Edition) on-prem farms — anonymous endpoint enumeration, version disclosure, legacy SOAP login bypass (Authentication.asmx), ToolShell precondition chain (CVE-2025-53770), SafeControl reflection enumeration via Picker.aspx, NTLM Type-2 AD topology disclosure, custom-branding module discovery, EoL farm permanent-CVE-window exploitation, FormDigest anonymous issuance, file-extension blocklist NOT-an-oracle pattern, custom-zone Forms auth bridging on-prem AD. Use when target has SharePoint headers (SPRequestGuid, X-MS-InvokeApp, X-SharePointHealthScore, MicrosoftSharePointTeamServices) or paths (/_layouts/15/, /_vti_bin/, /_api/, /_catalogs/).
Hunting skill for sqli vulnerabilities. Built from 12 public bug bounty reports including modern NoSQL injection (Rocket.Chat CVE-2021-22911 MongoDB $regex, Mongoose ORM CVE-2024-53900 $where bypass), modern ORM raw-fragment SQLi (Django CVE-2024-42005, Sequelize GHSA-wrh9-cjv3-2hpw), second-order SOQL injection (HackerOne Salesforce), time-based blind SQLi in GraphQL resolvers, and SQLi on OIDC-proxy backends. Use when hunting SQLi / NoSQLi on any target
Hunting skill for subdomain takeover vulnerabilities. Includes modern provider fingerprints — Microsoft Azure DevOps `cloudapp.azure.com` regional-pool re-issue (1-click OAuth ATO via wildcard `reply_to`, Binary Security), Zendesk help-desk takeover → email interception → password reset chain (0xprial writeup), Vercel `cname.vercel-dns.com` deleted-project takeover, plus general Fastly CDN service re-attach and S3 dangling-bucket cookie-scope techniques. Use when hunting subdomain takeover — emphasis on ATO-chain primitives (OAuth `redirect_uri`, cookie-domain, email DNS).
Detects T1547.001 startup folder persistence by monitoring Windows startup directories for suspicious file creation, cross-referencing Autoruns entries, and running a Python watchdog script for real-time filesystem monitoring. Use when hunting for malware or implants that survive reboot via startup-folder placement, or when validating autoruns/EDR findings against known-good startup baselines.
Use ksubdomain for stateless subdomain brute-forcing. Use it for extremely fast subdomain brute-forcing and validation. ksubdomain sends packets directly through raw network interface sockets and is 10 times faster than dnsx. It supports validation and enumeration modes and requires root privileges. Use this skill for any high-speed subdomain brute-forcing or large-scale subdomain validation.
Audits websites for compliance with the Brazilian LGPD (Law 13.709/2018). Validates privacy policy, cookie consent, data minimization, international transfer, data subject rights, third-party scripts, and analytics. Generates a report with a compliance score and priority fixes.
Implement Okta as a centralized cloud identity provider: configure SSO with AWS, Azure, and GCP, deploy phishing-resistant MFA with Okta FastPass, automate user provisioning/deprovisioning, and enforce adaptive access policies on device posture and risk signals. Use when standing up Okta SSO, rolling out FastPass MFA, automating identity lifecycle, or building risk-based conditional access for cloud environments.
Use nerva for high-performance service fingerprinting. Use it to identify the specific services running on open ports. nerva supports 120+ protocols (databases, remote access, message queues, industrial control, web, and more) and is an upgraded version of fingerprintx. Use this skill for any service identification, protocol probing, or port fingerprinting task.
Hardens the npm supply chain with lockfile discipline, Dependabot cooldowns and groups, per-package-manager install-script policies, provenance verification, npm token hygiene, and SHA-pinned Actions. Use when the user asks to secure dependencies, audit npm packages, respond to a compromised dependency, or pin Actions. Not for repository settings such as rulesets or secret scanning, or for publishing.
Generate LLVM libFuzzer FUZZ test cases for C/C++ projects, run 26 security specification reviews, and generate semantic seed data. Compatible with OpenHarmony / Linux / Android build systems. Trigger keywords: fuzz testing, generate fuzzer, create fuzz cases, fuzz specification checks, fuzz_test, LLVMFuzzerTestOneInput, seed data/corpus
Kernel-level proxy protection via proxy-ns — forces ALL traffic (TCP/UDP/DNS) through Tor using Linux network namespaces. Unlike proxychains, this works with Go/Rust/static binaries, prevents DNS leaks, and is impossible for applications to bypass. Includes Tor circuit rotation, IPv6 leak prevention, stealth headers, and jitter configuration. Use AT THE START of any pentest or recon engagement — before any probes that could leak your source IP. Setup once at the beginning of a session and run the entire toolchain inside the proxy-ns shell
Design and audit enterprise procurement security review readiness, vendor risk questionnaires, security evidence packets, DPAs, subprocessors, insurance, policies, SOC/ISO evidence, pen test summaries, AI/data-use answers, redlines, gap handling, and sales/legal/security handoff. Use when deals stall on vendor review or buyer assurance.
Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection with agent-browser. Use when a preview or production URL redirects to a Vercel login page, returns a protection 401 or 403, or needs short-lived Trusted Sources OIDC authentication instead of a static bypass secret or public exception.
Use when starting an assessment and you need to discover an application's full attack surface — subdomains, hosts, endpoints, technologies, exposed services, leaked credentials and secrets — on assets you own or are authorized to test. Feeds the threat model with real, not assumed, targets.
Builds compliance checklists for business scenarios involving GDPR, PIPL, or advertising/data laws. Outputs a structured checklist with check items, legal basis, risk levels, and actionable recommendations. Triggered by requests like "run a compliance check," "GDPR/PIPL compliance," "pre-launch review," "privacy impact assessment (PIA/DPIA)," or asking if a feature is compliant.
Reviews Remix v2 code for v1-shape meta exports (BREAKING in v2), cookie security gaps (httpOnly, secure, secrets rotation), auth gates in wrong layer, and missing CSRF. Use when reviewing meta/SEO, session, auth, or form-mutation code in a Remix v2 codebase.
Deep analysis of Git history: identify frequently changed hotspot files, analyze code ownership by contributor, and scan for leaked secrets. Triggered when users ask about Git analysis, code hotspots, who owns what code, secret scanning, security audits of commit history, or optimizing code review assignments.
Implements the GDPR Article 17 right to erasure (right to be forgotten) workflow, covering all six grounds for erasure, five exceptions, technical deletion versus anonymization decisions, and third-party notification under Article 19. Activate for erasure request, deletion request, right to be forgotten, Art. 17 queries.
Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs.
Attack methodology for Microsoft SCCM/MECM (Configuration Manager). Use when an SCCM site server, management point (MP), or distribution point (DP) is found on the internal network. Covers NAA credential extraction, task sequence passwords, PXE boot media, Client Push forced authentication, site server takeover, lateral movement through application deployment, AdminService API exploitation, and hierarchy takeover (CAS→Primary).
Comprehensive backend development skill for building scalable backend systems using NodeJS, Express, Go, Python, Postgres, GraphQL, REST APIs. Includes API scaffolding, database optimization, security implementation, and performance tuning. Use when designing APIs, optimizing database queries, implementing business logic, handling authentication/authorization, or reviewing backend code.
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.