Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Guidance for Microsoft Defender for Business (MDB) — the SMB-segment endpoint security product (≤300 employees), bundled with Microsoft 365 Business Premium and available as a standalone SKU. Covers what's included vs MDE Plan 1/2 (next-gen AV, EDR with simplified configuration, ASR, automated investigation and response, vulnerability management, web content filtering, attack surface reduction, mobile threat defense add-on), wizard-driven onboarding, server add-on for SMB servers, the simplified portal experience vs full Defender XDR, transition path to MDE P2 / E5 as the org grows, and integration with Microsoft 365 Lighthouse for MSP delivery. WHEN: Defender for Business, MDB, SMB endpoint security, M365 Business Premium security, MDB server add-on, simplified EDR small business, MSP Defender for Business, M365 Lighthouse Defender, SMB upgrade to MDE Plan 2. DO NOT USE for enterprise EDR (use defender-for-endpoint), Defender XDR cross-product investigation (use defender-xdr), or Defender for Servers / Cloud (use defender-for-servers).
Guidance for Microsoft Defender for Cloud — AI workload protection (AI-SPM and runtime threat detection for generative AI). Covers AI Security Posture Management (discovery of Azure OpenAI / Azure AI Foundry / Amazon Bedrock / Google Vertex AI resources, identification of grounding data exposure, model deployment posture), runtime threat detection on Azure OpenAI (prompt injection / jailbreak attempts, sensitive data leakage in prompts/responses, wallet abuse, credential leakage), integration with Azure AI Content Safety Prompt Shields, attack path analysis for AI workloads, alert investigation in Defender XDR, and pairing with Purview DSPM for AI (user side) and Azure AI Content Safety (model side). WHEN: Defender for Cloud AI, AI-SPM, AI workload protection, Azure OpenAI threat detection, prompt injection alert, jailbreak alert Azure OpenAI, AI wallet abuse, AI workload posture, Amazon Bedrock posture, Vertex AI posture, generative AI security Azure. DO NOT USE for end-user AI usage governance (use purview-ai-hub), content moderation API (use azure-ai-content-safety), or M365 Copilot rollout (use copilot-for-m365-readiness).
Methodology for disk forensics and anti-disk forensics. Understand how blue teams recover deleted files from disk, extract timelines and analyze file system artifacts, and how red teams perform anti-forensics (secure deletion, timestamp tampering, trace removal). Use when you need to evade disk forensics or perform disk analysis
MUST USE for any task involving the dotenvx CLI tool — encrypting .env files, running commands with injected env vars, managing secrets across environments, and decrypting at runtime. Use this skill whenever the user mentions dotenvx, dotenv encryption, DOTENV_PRIVATE_KEY, encrypted .env files, or the dotenvx encrypt/run/set/get/decrypt/keypair commands. Also trigger when the user wants to: commit .env files safely to git, stop sharing secrets over Slack/chat, encrypt environment variables with public-key cryptography, set up multi-environment .env configs (production/staging/ci), manage secrets in a monorepo with -fk flag, migrate from python-dotenv or plain dotenv to encrypted envs, inject env vars into any process across any language (Node, Python, Ruby, Go, Rust, etc.), or configure CI/CD pipelines (GitHub Actions, Docker) with encrypted env files. This skill contains the authoritative CLI reference — without it, responses will hallucinate non-existent commands and flags.
Guidance for Microsoft Entra External ID — the unified customer identity and access management (CIAM) and external collaboration platform that replaces Azure AD B2C (for new tenants) and consolidates B2B guest scenarios. Covers external tenant creation, user flows (sign-up/sign-in, password reset), custom branding, identity providers (Google, Facebook, Apple, SAML/OIDC), email OTP and passkey support, custom attributes, custom authentication extensions (replaces B2C custom policies), API connectors, Conditional Access for external users, self-service sign-up in workforce tenants, B2B collaboration vs B2B direct connect, cross-tenant access settings, and migration considerations from Azure AD B2C. WHEN: Entra External ID, CIAM Microsoft, customer identity, replace Azure AD B2C, B2B guest user, B2B direct connect, cross-tenant access settings, external tenant, self-service sign-up, custom authentication extension, social identity provider, partner collaboration Entra, external user lifecycle, guest user expiration. DO NOT USE for workforce identity (use entra-id), workforce governance (use entra-id-governance), or workforce CA (use conditional-access-mfa).
Guidance for Microsoft Entra Verified ID — verifiable credentials issuance and verification platform based on open standards (W3C Verifiable Credentials, DIDs, OpenID4VC). Covers issuer setup (tenant configuration, DID registration, signing key in Key Vault), credential schema design, rules and display files, issuance flows (QR / deep link), verification flows, Face Check biometric matching, integration with Entra ID for workforce onboarding and access, integration with verification partners, and use cases (employee verification, remote onboarding, low-friction account recovery, vendor/contractor identity proofing). WHEN: Entra Verified ID, verifiable credentials, decentralized identity, DID issuance, issue credential Entra, verify credential, Face Check, remote onboarding identity proofing, account recovery with VC, contractor identity verification, vendor verification, workforce onboarding VC. DO NOT USE for B2C/CIAM (use entra-external-id), workforce identity admin (use entra-id), or PKI/certificate design (use pki-design).
Methodology for attacking Microsoft Exchange mail servers. Use when an OWA (Outlook Web App) login page or Exchange admin panel is found, when Exchange is running on port 443, or when an Exchange server is discovered in the internal network. Use when a port scan finds 25/443/587/993/995 with an Exchange fingerprint. Covers OWA password spraying, ProxyLogon (CVE-2021-26855), ProxyShell (CVE-2021-34473), ProxyNotShell (CVE-2022-41040), mailbox search and export, GAL global address list extraction, and NTLM relay to Exchange. Exchange is one of the highest-value targets in domain penetration — you can obtain domain admin mailboxes, extract the address book of all staff, and gain SYSTEM privileges. Use this skill whenever /owa /ecp /autodiscover /mapi paths are found
Use when testing file-upload handling, server-side request forgery (SSRF), and insecure deserialization — upload bypasses (type/extension/content, polyglots, path traversal), SSRF to cloud metadata and internal services, and unsafe deserialization sinks. On apps you own or are authorized to test.
Generate SSH keys per team standards and return the public key. Ed25519 by default, RSA 4096 as fallback (RSA 2048 is never allowed); private keys are chmod 600 and named after the service. Use this skill whenever the user wants an SSH key, keypair, deploy key, or login key for a service or machine, or mentions ssh-keygen/puttygen — e.g. "generate ssh key", "create an ssh keypair", "make a login key for service xxx", "generate a deploy key" — even if they do not mention team standards. Prefers puttygen (.ppk/.pem/.pub); falls back to ssh-keygen.
Comprehensive Go code review skill for PR reviews, architecture assessment, and test quality analysis. Use when reviewing Go code to ensure adherence to Go best practices, security standards, and project-specific patterns. Applies to full PR reviews, single file/function reviews, architecture evaluation, and test code quality checks.
Reverse engineering and binary analysis with IDA Pro and ida-cli. Use when driving headless IDA workflows from the shell or from an agent loop: disassembly, decompilation, cross-references, struct recovery, type work, patching, FLIRT, IDAPython scripting, emulation-based call tracing, and devirtualization of commercial VM protectors (Themida / VMProtect / Code Virtualizer / WinLicense). Covers the ida-cli flat CLI, the router service, stdio + streamable HTTP transports, the installable skill bootstrap, and the bundled `vm_devirt.py` emulator. Supports PE, ELF, Mach-O, and firmware binaries.
Use iox for port forwarding and internal network tunneling. Use when you need to forward internal ports to the external network, establish a SOCKS5 tunnel, or relay traffic. iox is a single-binary, zero-dependency port forwarding/proxy tool supporting forward proxies, reverse proxies, port mapping and SOCKS5 proxies, and is particularly suited to building traffic tunnels in internal network penetration. It is lighter than frp/nps and more feature-complete than socat. Use this skill in scenarios involving port forwarding, internal network tunneling, SOCKS5 proxies, traffic relaying or tunnel building
Bypassing Istio Service Mesh security policies. Use when the target K8s cluster uses Istio, when requests are rejected by an AuthorizationPolicy (403 RBAC denied), or when an Envoy sidecar is found. Core technique: UID 1337 bypasses Envoy. Use this skill for any scenario in K8s involving Istio policy blocks, Service Mesh restrictions, or Envoy-related security controls
Receive and secure Mailchimp webhooks. Use when setting up Mailchimp webhook handlers, responding to Mailchimp's GET URL validation, securing the endpoint with a URL secret, or handling audience events like subscribe, unsubscribe, profile, upemail, cleaned, and campaign.
Malware analysis methodology. Use when you need to analyze suspicious binaries (PE/ELF/Mach-O), malicious code in memory dumps, or samples of known malware families. Covers the full process of static analysis, dynamic analysis, code reversing and IOC extraction. Red team perspective: understand the detection surface to improve evasion
Use mapcidr for CIDR range processing. Use when you need to expand CIDRs into IP lists, aggregate IPs into CIDRs, slice ranges, count IPs, or shuffle IP order. mapcidr is a CIDR processing tool from ProjectDiscovery supporting IPv4/IPv6. Use this skill in any scenario involving CIDR calculations, IP list processing or range slicing
Collect Active Directory data with SharpHound and Entra ID data with AzureHound, ingest into BloodHound Community Edition, and analyze on-prem, cloud, and hybrid attack paths using built-in queries and custom Cypher. Use during authorized red-team or penetration-test engagements to map privilege-escalation chains toward domain/tenant compromise.
Network flow extractor that analyzes pcap/pcapng files to identify outbound connections with automatic DNS hostname resolution. Use when you need to enumerate network destinations, identify what hosts a device communicates with, or map IP addresses to hostnames from packet captures.
Exploiting vulnerabilities in domestic Chinese OA/internal network systems. Use when domestic Chinese OA systems such as Seeyon, Weaver (E-cology), Yonyou (NC/U8), Landray, Tongda, Ezoffice, Kingdee or iOffice are discovered in the internal network. Covers typical vulnerabilities, default credentials and RCE paths for each system. They appear frequently in domestic HW/competition internal networks, so be sure to use this skill
Configure LangWatch online evaluations and guardrails for production traffic. Use when the user wants to score live traces or threads, monitor production quality, sample incoming traffic, or synchronously block unsafe requests and responses. Do not use for batch experiments.
Exploiting misconfigured object storage (S3/OSS/COS/OBS) buckets. Use when object storage services such as AWS S3, Alibaba Cloud OSS, Tencent Cloud COS or Huawei Cloud OBS are found, or when headers such as x-amz-*, x-oss-*, x-cos-* appear in HTTP responses. Covers bucket enumeration, ACL misconfiguration detection, public read/write exploitation, bucket takeover, object traversal, arbitrary file upload and Policy abuse. Use this skill whenever assets or URLs related to cloud storage buckets are found (*.s3.amazonaws.com, *.oss-cn-*.aliyuncs.com, *.cos.*.myqcloud.com, etc.). Prefer coscli/tccli for Tencent Cloud COS and awscli for AWS S3
Conduct cybersecurity assessments of upstream, midstream, and downstream oil and gas operations, covering pipeline SCADA, refinery DCS, safety instrumented systems, and remote wellhead RTUs, and evaluate compliance with API 1164, TSA Pipeline Security Directives, and IEC 62443. Use when assessing a refinery, pipeline, or production facility or preparing for TSA/API compliance audits; not for IT-only or purely physical-security assessments.
Use when modifying the BK-CI IAM RBAC permission model, such as adding resource types, designing action lists, configuring IAM resources, backfilling migration data, and validating callback chains. Prefer this when the user needs to change the permission model rather than make ordinary permission calls.
Receive and verify Recurly webhooks. Use when setting up Recurly webhook handlers, verifying the recurly-signature header (HMAC-SHA256), securing the endpoint with HTTP Basic Auth, or handling subscription and billing events like new_subscription_notification, updated_subscription_notification, successful_payment_notification, and failed_payment_notification.
Reverse engineer and security-review Chrome/Firefox browser extensions — unpacking the CRX/XPI, reading the manifest for over-broad permissions, and tracing the trust boundary between page, content script, background service worker, and native messaging host. Use when analyzing a suspicious or over-permissioned extension, auditing your own extension's privilege model, or investigating how a content script exposes privileged APIs to a web page
Builds the "RHDH CVE Management - <version>-plugins.csv" export by walking `rhdh-plugin-export-overlays` git history on a release branch since a revision, scoped to generally-available plugin workspaces, then enriching each CVE from Jira RHIDP, RHDHBUGS, and RHDHPLAN. Use for "generate the plugin overlay CVE CSV for 1.10.3", "what CVEs were fixed in plugins since 1.10.2", or "rebuild the plugin CVE list with the ProdSec CVSS scores".
Rust security patterns for web applications. Covers memory safety guarantees, dependency auditing, secure coding practices, and OWASP for Rust ecosystem. USE WHEN: user works with "Rust", "Actix", "Axum", "Rocket", "Warp", asks about "Rust vulnerabilities", "cargo audit", "Rust injection", "Rust authentication" DO NOT USE FOR: general OWASP concepts - use `owasp` or `owasp-top-10` instead, other language security - use language-specific skills
Integrate Seam Access Grants for per-entrance, per-credential control over smart lock access. Create access grants specifying who gets access to which doors, when, and how (PIN code, mobile key, Instant Key). Use this skill when someone needs to control which access methods each guest or member gets, issue both PIN codes and mobile keys, manage access per-door (room + lobby + gym), or deliver Instant Key links. Works with August, Yale, Schlage, Kwikset, and other smart locks. Common use cases: hotel guest apps, gym/fitness access, office visitor management.
Use this skill whenever auditing, reviewing, or testing Python web applications (FastAPI or Flask) for OWASP A09:2025 — Security Logging & Alerting Failures. Trigger this skill when the user mentions: logging security, audit trails, log injection, sensitive data in logs, alerting gaps, insufficient logging, SIEM integration, log monitoring, incident detection readiness, or any request to audit or fix logging/alerting in a Python backend. Also trigger when a user asks "are we logging the right things?", "how do I detect attacks?", or "what should we be alerting on?". Do NOT skip this skill just because the request sounds simple — log-related security issues are consistently underestimated and require systematic coverage across all five CWEs.
Use when you want to security-test, pentest, audit, or find vulnerabilities in an application you own or are authorized to test — entry point that confirms authorization and routes to the right phase (threat model, code audit, active test, or hardening).
Serverless/cloud function security testing and attacks. Use when the target involves Serverless services such as AWS Lambda, Tencent Cloud SCF, Alibaba Cloud FC, or Azure Functions. Use when the API Gateway backend is found to be Lambda/SCF triggered, when function operation permissions are obtained via cloud-aksk-exploit, or when vulnerabilities in cloud function code need to be analyzed. Covers event injection (parameter tampering of HTTP/OSS/message queue triggers), environment variable leakage (hardcoded credential extraction), function code injection/overwriting (UpdateFunctionCode), runtime exploitation (/tmp writes/Layer hijacking/dependency poisoning), and temporary credential abuse. Use this skill whenever any Lambda/SCF/cloud function, API Gateway, or Serverless architecture is discovered
Use when asked to audit, measure, or re-check how agent sessions are using the Bash tool — command chaining (&&, ;, |), cd into the session's own repo, head/tail truncation, sed -n/cat/heredoc instead of Read/Edit, git commit/push inside chains or behind git -C — or when deciding whether a permission prompt, an allowlist rule, a ~/.agents/AGENTS.md Bash rule, or the permission mode (acceptEdits vs auto) needs changing and wants evidence from real transcripts rather than a hunch. Runs a stdlib script over ~/.claude/projects/*.jsonl, prints per-model and per-session rates plus samples, and carries the dated research that explains why each pattern happens and where the fix belongs. Also the place to record a newly noticed Bash anti-pattern so the next audit measures it.
Security testing skill for OWASP A08:2025 — Software or Data Integrity Failures in Python web applications (FastAPI and Flask). Use this skill whenever the user wants to audit, detect, test, or fix integrity vulnerabilities including: insecure deserialization (pickle, yaml, jsonpickle, dill), mass assignment flaws, untrusted CDN/module inclusion, unsigned updates, CI/CD pipeline integrity, or Subresource Integrity (SRI) checks. Trigger this skill for ANY task involving pickle/deserialization security, CWE-502, CWE-915, CWE-829, CWE-345, or CWE-494, even if the user doesn't explicitly mention OWASP A08.
Expert guidance on detecting, assessing, and remediating Software Supply Chain Failures (OWASP A03:2025) in Python applications — the highest-exploit-score category in the 2025 OWASP Top 10. Use this skill whenever the user mentions dependency scanning, vulnerable packages, SBOMs, pip-audit, safety check, lockfile integrity, hash pinning, transitive dependencies, CI/CD pipeline security, compromised packages, supply chain attacks (SolarWinds, Log4Shell, typosquatting), or requests a security review of requirements.txt / pyproject.toml. Also trigger for any question about CWE-1104, CWE-1395, or CWE-1329.
Orchestrates the insight operations workflow: calls review for human qualitative assessment (L2), drafts customer delivery notes, confirms write-back, and queries delivery tickets and comments for Q&A. Use for handling pending tasks, submitting existing conclusions, customer briefings, or following up on EMDR. Insight interpretation and evidence gathering are handled by review; it does not handle endpoint remediation, ticket creation, or ticket status changes.
Conduct a challenging review and read-only evidence gathering on suspicions raised by AI/Agent assessment (L1), independently confirming, correcting, or overturning its incident and compromise determinations to produce a human classification (L2). When analyzing an insight with an existing L1, proceed by default with the minimum necessary verification. For IOA with an existing L1, try to freeze the evidence package (AI assessment evidence and AI classification evidence); otherwise, use the online path. Does not handle write-back or ticket closure.
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.