Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
GitHub AI-powered security and automation features (2025-2026). Proactively activate for: (1) GitHub Copilot in PRs (Copilot code review, Copilot autofix), (2) GitHub Advanced Security (CodeQL, secret scanning, dependency review), (3) Copilot Workspace, (4) GitHub Models (gh models eval, prompt evaluations), (5) GitHub Copilot CLI 2.x, (6) AI-assisted issue triage, (7) Copilot extensions and skillsets, (8) Copilot Enterprise context (knowledge bases), (9) automated dependency updates (Dependabot AI grouping), (10) Spark for app generation. Provides a feature catalog, Copilot CLI command reference, gh models eval examples, GHAS configuration, and Copilot Workspace usage
Offensive methodology for attacking GraphQL APIs during penetration tests and bug bounty engagements. Covers the full attack lifecycle: endpoint discovery, introspection abuse and blind schema reconstruction when introspection is disabled, authentication and authorization bypass through Relay node IDs and nested object traversal, injection via variables and directives, query batching for brute force and OTP bypass, denial of service through depth bombs and alias amplification, WebSocket subscription hijacking, information disclosure through verbose errors and field suggestion oracles, and file upload abuse via the multipart GraphQL specification. Includes tool-specific guidance for InQL, graphql-cop, CrackQL, BatchQL, Altair, GraphQL Voyager, and clairvoyance. Trigger on: GraphQL, graphql, introspection query, batching attack, query depth, GraphQL injection, GraphQL IDOR, field suggestion, GraphQL auth bypass, GraphQL DoS, GraphQL security, graphql-cop, InQL, CrackQL, BatchQL, Relay node, alias amplification, subscription abuse, multipart upload GraphQL, schema enumeration, __schema, __type.
Guidance for designing secure APIs on Azure - authentication, authorization, gateway controls, input validation, rate limiting, secret management, and runtime threat detection - aligned to OWASP API Security Top 10 and Azure API Management. WHEN: API security design, secure API, OWASP API Top 10, API authentication, API gateway security, rate limiting, validate JWT, protect backend API, API Management security policies, secure API architecture, BOLA, BFLA. DO NOT USE for general application security or web app design (use security-architecture / threat-modelling) or for API runtime detection only (use defender-for-apis).
Configure SAML 2.0 identity federation between on-premises Active Directory (via AD FS or a third-party IdP) and Microsoft Entra ID, covering federation models (AD FS, password hash sync, pass-through auth, third-party IdP) and the SAML authentication flow. Use when extending on-premises authentication authority to cloud resources or designing hybrid identity SSO architecture for Entra ID.
Discovers and exploits broken link hijacking by spidering a site (Burp Suite Spider, Scrapy, curl scraping), extracting referenced external scripts/domains, and checking DNS/CNAME records and domain registration status for expired or unclaimed resources an attacker could register. Use for subdomain takeover testing, supply-chain review of third-party scripts, or bug bounty hunting for hijackable external resources.
Use when about to consume content from any external/untrusted source — files from externally-cloned repos, WebSearch results, WebFetch responses, or fetched files. Identifies and neutralizes prompt-injection attempts via hybrid regex + LLM detection. Returns sanitized content plus a structured report. Maintains a persistent flagged-sources document at docs/security/flagged-sources.md that turns repeat-offender sources into automatic caution-bumps. Severity-keyed action: low and medium are removed (replaced with [REMOVED: marker]), high aborts the whole sanitization. Flagged content is never echoed back to the caller. One layer of defense in depth — combine with synthesis guard rails and user review. Hand-authored, security-critical.
Analyze CDN domain traffic anomalies using hcloud CLI. Query billing mode and traffic/bandwidth metrics for specified domains, compare against 3-month baseline and absolute thresholds to identify traffic theft or abuse. Use this skill when the user wants to: (1) analyze CDN domain traffic anomalies, (2) check if a domain has traffic theft or abuse, (3) query CDN billing mode and traffic/bandwidth metrics, (4) compare current traffic against historical baseline. Triggers include: "CDN流量异常", "流量异常分析", "域名流量分析", "流量盗刷", "带宽异常", "95带宽异常", "流量突增", "流量对比", "基准分析", "traffic anomaly", "bandwidth anomaly", "CDN traffic analysis", "traffic theft detection", "baseline comparison"
Guide for connecting Infisical to an identity provider for human login and user provisioning. Covers Google and GitHub SSO (free), SAML 2.0 and OIDC (paid) with Okta, Azure/Entra ID, JumpCloud, Google, Auth0, Keycloak, PingOne, GitLab, LDAP login, SCIM user and group provisioning with Okta/Azure/JumpCloud/PingOne/PingFederate, SAML and OIDC group membership mapping, SCIM group to organization role mappings, the mandatory email domain verification prerequisite, SSO enforcement and its effect on password signup, and the /login/admin break-glass portal. Use this skill when someone asks about: Infisical SSO, SAML login, OIDC login, Okta or Azure AD integration, SCIM provisioning, syncing identity provider groups into Infisical, enforcing SSO, or being locked out after enabling SSO. For HUMAN login and user provisioning. Not for machine identity auth methods, including OIDC and LDAP for workloads (infisical-setup), nor for roles and permissions (infisical-access-control).
Insecure deserialization exploitation across Java, PHP, .NET, Python, Node.js, and Ruby. Covers gadget chain construction with ysoserial/phpggc/ysoserial.net, ObjectInputStream and BinaryFormatter sink identification, pickle __reduce__ RCE, phar:// wrapper abuse, Jackson polymorphic typing, Json.NET TypeNameHandling, ViewState tampering, node-serialize IIFE injection, Ruby Marshal.load and YAML.load gadgets, framework-specific chains for Spring/Hibernate/Laravel/Symfony, modern attack surfaces including Kubernetes admission webhooks and message queue consumers, WAF bypass through encoding layers and content-type manipulation, and serialVersionUID/JMX/RMI vectors. Activate when the engagement involves deserialization sinks, serialized data in cookies or request bodies, gadget chain development, magic method abuse, ysoserial payload generation, or any review of marshalling and unmarshalling logic in target applications.
Administer an Omni Analytics instance — manage connections, users, groups, user attributes, permissions, schedules, and schema refreshes via the Omni CLI. Use this skill whenever someone wants to manage users or groups, set up permissions on a dashboard or folder, configure user attributes, create or modify schedules, manage database connections, refresh a schema, set up access controls, provision users, or any variant of "add a user", "give access to", "set up permissions", "who has access", "configure connection", "refresh the schema", or "schedule a delivery".
Runs a security scan on a deployed Power Pages site, fetches the latest scan report, and produces a plain-language summary. Scans the live site's public surface for vulnerabilities and surfaces issues by severity. Use when the user wants to scan, check, test, audit, or assess a published site, find vulnerabilities on production, view the latest scan report, see previous scan results, run a security audit, or asks "how safe is my live site?", "is my site vulnerable?", "audit my production site" — even if they say "find issues" or "check for problems" without mentioning "scan" or "security".
Use when building or auditing a Telegram Mini App: server-side initData verification, sendData, in-app Stars payments, viewport and safe areas. Not for the bot (telegram-bots) or user accounts (telegram-userbots). Opt out: no telegram, без телеграма. Triggers - "mini app", "initData", "мини-апп".
This skill should be used when the user asks to “pentest WordPress sites”, “scan WordPress for vulnerabilities”, “enumerate WordPress users, themes, or plugins”, “exploit WordPress vulnerabilities”, or “use WPScan”. It provides comprehensive WordPress security assessment methodologies.
End-to-end XRPL development playbook. Covers XRP Ledger dApp development, including project scaffolding (create-xrp), wallet integration (xrpl-connect), client SDKs, transactions, tokens, NFTs, DEX/AMM, cross-chain interoperability (Axelar), and security best practices
Solution skill for using WAF to protect web applications on ECS. Used for quickly deploying network environments including VPC, security groups, and ECS instances, and integrating WAF for web application protection. Trigger words: "WAF protection", "ECS web protection", "Web Application Firewall", "website security"
Use this skill when the user is deploying or operating the DOCA Argus Service—the packaged BlueField-side runtime-security container that watches the BlueField and attached host for suspicious activity, integrity violations, and operational anomalies, and forwards findings to a SIEM (Splunk / ELK / Sentinel / syslog). Covers the four-axis config (detection policy, forwarding, sampling, host coverage), running the NGC container on BlueField Arm, and wiring the forwarder. Trigger even without "DOCA Argus" by name—typical implicit phrasings: "container green but no findings arrive", "false-positive flood in Splunk", or "runtime security on a fleet of BlueField-3s". Refuse and route elsewhere for installing DOCA, SIEM-side ingest stanzas, pre-baked detection-rule packs, and metrics observability (DOCA Telemetry). Argus is NVIDIA's currently promoted runtime-security framework, superseding the older App Shield library; name it first for new runtime-security work.
Use this skill when the user asks to “learn ethical hacking,” “understand penetration testing lifecycle,” “perform reconnaissance,” “conduct security scanning,” “exploit vulnerabilities,” or “write penetration test reports.” It provides comprehensive ethical hacking methodology and techniques
Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.
Dense description covering Server-Side Template Injection across Jinja2, Twig, Freemarker, Velocity, Pebble, Smarty, Mako, Handlebars, ERB, Thymeleaf, EJS, Pug. Engine fingerprinting, filter bypass, blind exploitation, WAF evasion, SSTI-to-RCE chains. Tools: tplmap. CWE-1336. MITRE T1190. Use when testing template rendering endpoints or exploiting template injection for code execution.
Use when setting pythia up for a project or a machine - writing connections.json, creating a least-privilege agent user, wiring the SQLcl MCP server, or diagnosing a connection that will not open. Also the place to start when check prints a privilege warning.
Execute a comprehensive, framework-agnostic Security Audit. Detects project type at runtime and adapts security checks accordingly. Analyzes sensitive files, source code secrets, and dependency vulnerabilities. Produces a severity-classified report. Use when the user asks to audit security, scan for vulnerabilities, check for secrets, or assess dependency risks. Triggers on: 'security audit', 'vulnerability scan', 'secret scan', 'dependency audit', 'security check', 'pentest', 'owasp'.
Build automated IOC enrichment pipelines in Splunk Enterprise Security by ingesting threat feeds into KV Store collections and correlating them against security events via lookup tables, modular inputs, and the Threat Intelligence Framework. Use when wiring threat intel into Splunk correlation searches to flag IOC matches and reduce SOC triage time.
Detect and prevent dependency confusion (public-over-private package name resolution) in npm, PyPI, and Maven by enumerating claimable internal package names with tools like `confused` and OWASP `dep-scan`, then enforcing source restrictions via `.npmrc`, `pip.conf`/`pyproject.toml`, and Maven `settings.xml`. Use when onboarding a repo to a supply-chain security program, auditing lockfiles/manifests for confusable dependencies, or after an incident that may have leaked internal package names.
Use this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configuring `doca_aes_gcm_task_encrypt` / `_task_decrypt`, querying `doca_aes_gcm_cap_*` for per-key-type (only `DOCA_AES_GCM_KEY_128` / `_256` — AES-192 not supported) and per-task support, sizing plaintext against the max-buf cap, setting source / destination mmap permissions, validating with a NIST GCMVS or RFC 5288 vector, or debugging DOCA_ERROR_* including the security-critical tag-verification-failed outcome on decrypt. Trigger even when the user does not explicitly mention "DOCA AES-GCM" or "AEAD" — typical implicit phrasings: "decrypt completion IO_FAILED", "auth tag isn't verifying", "NOT_PERMITTED on my encrypt buffer", "is AES-192-GCM on this BlueField" (no), or "encrypted record came back tampered". Refuse and route elsewhere for non-GCM AES modes (CBC / CTR / XTS — CPU OpenSSL), key management (KMS / HSM / rotation), SHA (doca-sha), or general AEAD background.
Use when wiring error tracking into a service: the Sentry SDK, DSN placement, secret scrubbing, releases tied to commits. Not for agent trajectories (agent-evals) or uptime vendors. Opt out: no wiring, без обвязки. Triggers - "add Sentry", "SENTRY_DSN", "подключить Sentry", "трекинг ошибок"
Infrastructure as Code security scanning for Terraform, Kubernetes, CloudFormation, and Azure ARM. Detects misconfigurations, security risks, and compliance violations before deployment. Use when: - User asks to scan Terraform files or modules - User mentions "infrastructure security" or "IaC scan" - User is working with Kubernetes manifests - User asks about CloudFormation or ARM template security - Agent is generating or modifying infrastructure code
Guide for the Infisical Gateway and Relay — reaching private network resources (VPC-only databases, on-premises directories, internal APIs, HSMs) from Infisical without any inbound firewall rules. Covers the gateway/relay architecture using SSH reverse tunnels, exact ports and egress allowlist requirements (TCP 2222 to the relay, TCP 443 to Infisical, TCP 8443 platform-to-relay), deployment with `infisical gateway start` and `infisical gateway systemd`, Infisical-managed vs self-deployed relays, Gateway Pools for high availability, health checks and heartbeat intervals, and which features and App Connection types can be routed through a gateway. Use this skill when someone asks about: Infisical Gateway, relay server, accessing a private database from Infisical, dynamic secrets for a database with no public endpoint, gateway pools, or 'Infisical cannot reach my internal resource'. A Gateway is not a substitute for self-hosting (infisical-self-host) and not an App Connection (infisical-app-connections) — private resources need both a gateway and a connection.
Guide for Infisical KMS — managing cryptographic keys and performing encrypt/decrypt, sign/verify, and HMAC operations without the key ever leaving the platform. Covers KMS key creation with the three key usages (encrypt-decrypt, sign-verify, generate-verify-mac), symmetric algorithms (aes-256-gcm, aes-128-gcm), asymmetric algorithms (RSA_4096, ECC_NIST_P256/P384/P521, post-quantum ML_DSA_44/65/87), signing algorithms (RSASSA_PSS, RSASSA_PKCS1_V1_5, ECDSA, ML-DSA), HMAC algorithms, key rotation, exportable keys, external KMS backing with AWS KMS or GCP KMS, KMIP server integration, Kubernetes encryption-at-rest, and Sigstore cosign signing. Use this skill when someone asks about: Infisical KMS, encrypting data with a managed key, envelope encryption, sign and verify with Infisical, HMAC, KMIP, external KMS, or 'how do I encrypt data without handling the key'. For doing cryptography with a key Infisical never releases. Not for storing a value and reading it back, which is a secret (infisical-setup), nor for X.509 certificates (infisical-pki).
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI namespace attacks through --extra-index-url resolution ordering, NuGet feed priority exploitation when multiple package sources are configured without clear directives, Maven and Gradle repository ordering where artifact resolution traverses repositories sequentially, Go module proxy abuse through GOPROXY misconfiguration, Ruby gems namespace squatting, and Docker image tag confusion with unqualified image references. Provides complete proof-of-concept methodology using safe callbacks including DNS canary via interactsh or Burp Collaborator and HTTP beacon with no destructive payload. Covers reconnaissance techniques for discovering internal package names through GitHub repository analysis, error message harvesting, JavaScript source map extraction, lock file parsing, job postings mentioning internal tools, and package manifest inspection. Directly references and builds upon Alex Birsan's seminal 2021 dependency confusion research. Each ecosystem section includes registry-specific exploitation mechanics, configuration vulnerabilities, and defensive countermeasures for engagement reporting.
Enhance PRDs, feature specs, user stories, or product briefs with explicit OWASP ASVS coverage and FIASSE v1.0.4 SSEM implementation guidance — before code is written. Trigger on "harden the PRD/spec", "choose ASVS level", "map features to ASVS", "find missing security requirements", "add NFRs for security", "make these requirements securable", "security-review my product brief". For code review use securability-engineering-review; for code generation use securability-engineering.
Use when reviewing code for security before merging or shipping, and when a change touches untrusted input, authentication, authorization, secrets, SQL, subprocess execution, file paths, outbound requests, deserialization, uploads, or third-party dependencies. Triggers include "security review", "is this safe", "can this be exploited", "audit this for vulnerabilities", and adding any new external interface — an endpoint, a webhook, a plugin, or a tool an LLM can call.
Run an autonomous AI penetration test with Strix against a codebase, repository, URL, domain, or IP — either self-hosted with the open-source CLI or via the managed app.strix.ai cloud API — and read the validated findings (Markdown, JSON, CSV, SARIF, PoCs). Use when the user asks to pentest, security-scan, or find vulnerabilities in an app, API, website, or repo with Strix.
Expert knowledge for Azure External Attack Surface Management development including configuration. Use when filtering EASM inventory by ASN, domains, hosts, IPs, pages, SSL certs, or exporting findings to analytics tools, and other Azure External Attack Surface Management related development tasks. Not for Azure Defender For Cloud (use azure-defender-for-cloud), Azure Security (use azure-security), Azure Sentinel (use azure-sentinel), Azure Networking (use azure-networking).
[AUTO-INVOKE] MUST be invoked BEFORE deploying DeFi contracts (DEX, lending, staking, LP, token). Covers anti-whale, anti-MEV, flash loan protection, launch checklists, and emergency response. Trigger: any deployment or security review of DeFi-related contracts.
Simulates a batch of proposed IAM policy changes using Google Cloud Policy Simulator. Takes an array of simulations (resource, member, proposed_policy or proposed_policy_file), runs the simulation replay, and returns mapped results. Use when you have a batch of proposed IAM policy changes and need to simulate their impact on recent access patterns using Google Cloud Policy Simulator. Don't use for analyzing live IAM policies, applying policy changes, or simulating individual policy changes without a batch structure.
Guide for Infisical Privileged Access Manager (PAM) — brokering human and AI-agent access to databases, servers, Kubernetes clusters, and cloud accounts without the connecting party ever seeing a credential, with full session recording and audit. Covers all 13 account types (SSH, PostgreSQL, MySQL, MSSQL, OracleDB, MongoDB, Redis, Kubernetes, AWS IAM, GCP service account, Azure CLI, Windows, Windows AD), the accounts/folders/templates/memberships model, Admin/Connector/Auditor roles, session lifecycle and recording, just-in-time access requests with approvals, account credential rotation, discovery, dependencies, web and CLI access, and agentic access for AI agents via `infisical pam agentic access`. Use this skill when someone asks about: Infisical PAM, privileged access, session recording, just-in-time database access, brokered SSH access, giving an AI agent database access safely, access requests and approvals for infrastructure, or 'how do I let someone into production without giving them the password'. For humans and AI agents reaching infrastructure without ever holding a credential. Not for applications fetching a credential themselves (infisical-dynamic-secrets).
Inspects and configures the web application firewall (WAF) in front of a Power Pages production site. Lists the current state, recommends enabling protection when it is off, and walks the user through adding, updating, or removing custom rules — IP blocks, country blocks, path blocks, and rate limits. Use when the user wants to turn on WAF, block traffic by IP or country, rate-limit login or signup pages, protect pages from brute-force attempts, restrict access to specific paths, review the current firewall configuration, or asks "is my site protected against bots / common web attacks?" — even if they say "add rate limit" or "protect login page" without mentioning "firewall" or "WAF".
Inspects and configures the security headers a Power Pages site sends to browsers — Content Security Policy, frame and clickjacking protection, cross-origin sharing, cookie behavior, and related site settings. Identifies gaps and walks the user through fixes. Use when the user wants to review headers, fix CSP errors, allow embedding in another site, control cross-origin access, harden cookie settings, or asks "are my browser settings safe?", "fix my CSP", "set up CORS" — even if they only mention a specific header name without saying "security headers".
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.