Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Analyze email messages and mailbox data for forensic investigation. Use when investigating phishing attacks, business email compromise, insider threats, or any scenario requiring email evidence analysis. Supports PST, OST, MBOX, EML, and MSG formats.
Guidance for Microsoft Entra Global Secure Access (GSA) — Microsoft's Security Service Edge (SSE) combining Entra Internet Access (SWG/Secure Web Gateway) and Entra Private Access (ZTNA replacement for VPN). Covers client deployment (Windows, macOS, iOS, Android), traffic forwarding profiles (Microsoft, Internet, Private), Conditional Access for network traffic, source IP restoration, app discovery, Quick Access and per-app access for Private Access, connector deployment, branch site connectivity (IPSec), TLS inspection, and Universal CA integration. WHEN: Entra Global Secure Access, GSA, Microsoft SSE, Entra Internet Access, Entra Private Access, ZTNA Microsoft, replace VPN with ZTNA, secure web gateway Entra, Conditional Access on network, source IP restoration, Quick Access app, Private Access connector, branch IPSec to Microsoft, GSA client rollout. DO NOT USE for general Conditional Access policy design (use conditional-access-mfa), Azure VPN/ExpressRoute design, or third-party SSE (Zscaler/Netskope) configuration.
Escape containers that drop capabilities, enforce seccomp profiles, and run behind AppArmor or SELinux. Techniques include enumerating residual capabilities, analyzing seccomp filters, abusing single-capability escapes, cgroup release agents, filesystem mounts, and runtime CVEs. Use when a container has no --privileged flag but retains exploitable capabilities, seccomp or LSM blocks standard escape paths, targeting gVisor or Kata sandboxes, or reviewing a hardened container deployment for residual attack surface.
Comprehensive intranet scanning and exploitation with fscan. When you have an intranet foothold and need host discovery, port scanning, weak credential brute-forcing, or vulnerability detection, fscan is the first choice — a single zero-dependency binary that completes the full host discovery + port + service + weak credential + POC workflow in one command. It also supports post-exploitation operations such as Redis public key/scheduled task writing, SSH command execution, MS17-010 exploitation, Pass-the-Hash, and WMI remote execution. Use this skill for any scenario involving intranet scanning, subnet probing, bulk weak credential detection, intranet vulnerability scanning, domain controller identification, or NetBIOS probing. Even if you just want a quick look at which hosts are alive on a subnet, prefer fscan over nmap
AI-powered code vulnerability analysis and dependency scanning using Gemini CLI security extension patterns. Detects hardcoded secrets, injection attacks, weak cryptography, authentication flaws, and LLM prompt injection. Also scans dependencies against the OSV.dev vulnerability database.
Technical safeguards and architectural patterns for building HIPAA-compliant software on AWS. Use when building healthcare SaaS, handling PHI (Protected Health Information), designing patient data systems, implementing healthcare APIs, setting up HIPAA-eligible AWS infrastructure, reviewing code for PHI exposure, designing audit logging, or when the user mentions patients, medical records, EHR/EMR, health data, HL7, FHIR, or covered entities. Essential for founders and developers building in healthcare or digital health space.
Runs a hypothesis-driven threat hunt for Windows Scheduled Task persistence (T1053), guiding SIEM/EDR queries against task creation events (e.g. Event ID 4698), suspicious task actions, and unusual scheduling patterns. Use when hunting for scheduled-task persistence, after threat intel flags related campaigns, during incident response, or when alerts fire on schtasks/at.exe activity.
Runs a hypothesis-driven threat hunt for Volume Shadow Copy deletion (T1490) by querying SIEM/EDR telemetry for vssadmin, wmic shadowcopy, and PowerShell shadow-copy-deletion commands. Use when hunting for ransomware preparation or anti-forensics activity, after threat intel flags active campaigns, or when alerts trigger on shadow-copy deletion commands.
Guides designing, deploying, and measuring an anti-phishing security awareness program - baseline phishing simulations, interactive training modules, just-in-time learning, and metric tracking - using platforms like KnowBe4, Proofpoint Security Awareness, or Cofense. Use when building or maturing a phishing awareness program, establishing training controls for compliance, or measuring phishing susceptibility and reporting rates over time.
Expert Python security testing skill for OWASP A05:2025 — Injection vulnerabilities in FastAPI and Flask applications. Use this skill whenever the user asks about: SQL injection, XSS, SSTI (Server-Side Template Injection), OS command injection, ORM injection, LLM prompt injection, input validation, parameterized queries, Jinja2 escaping, or any untrusted data reaching an interpreter (database, OS shell, template engine, or browser). Also trigger for security audits, pen testing, Bandit SAST scans, code review for injection flaws, or any request to "find injection bugs", "check for SQLi", "audit my Flask/FastAPI app", or "scan for command injection". This skill has the highest CVE count of all OWASP categories (62,445) — always apply it proactively when reviewing Python web application security.
Collect, organize, and validate evidence for ISO 27001 and SOC 2 audits. API-first approach with CLI commands for major cloud platforms. Produces timestamped, auditor-ready evidence packages. Use when user says "collect audit evidence," "prepare evidence package," "evidence for the auditor," "refresh evidence," or "evidence gap analysis."
Local resource library navigation — the structure and usage of the dictionary library (Dic), payload library, and POC library. Essential reading when you need directory brute-forcing with ffuf/spray, password brute-forcing, or building fuzz payloads. Covers dictionary selection strategy, payload template invocation, and POC library search methods. The dictionary library is installed uniformly under /pentest
Supplies the approval rule another RHDH skill applies when it is already about to change something outside the session: how to state each operation, what approval binds to, what to report afterwards, and how to keep credentials out of a plan preview. Cited by name from the skill doing the work. Not an entry point — it performs no forge, Jira, or repository action itself, and a request to open, comment, transition, push, or post belongs to the skill that owns that target.
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
Guidance for rolling out passkeys (device-bound and synced) and FIDO2 security keys in Microsoft Entra ID as the primary phishing-resistant authentication method. Covers passkey types (device-bound in Microsoft Authenticator, synced passkeys via platform providers, hardware security keys), Conditional Access authentication strength, registration campaigns, Temporary Access Pass (TAP) bootstrapping, lifecycle (lost device, attestation), Conditional Access requiring phishing-resistant MFA, decommissioning legacy methods (SMS, voice, weaker app push), and integration with Windows Hello for Business. WHEN: passkey rollout, FIDO2 keys, phishing-resistant MFA, Microsoft Authenticator passkey, device-bound passkey, synced passkey, Temporary Access Pass, TAP, Conditional Access authentication strength, kill SMS MFA, retire voice MFA, passwordless rollout, FIDO2 attestation, security key registration. DO NOT USE for general CA policy authoring (use conditional-access-mfa), Windows desktop sign-in design end-to-end (use windows-hello), or Verified ID issuance (use entra-verified-id).
Privilege persistence methodology. Use when you have obtained access to a target system and need to maintain long-term access. Covers Linux (cron/SSH key/webshell) and Windows (scheduled task/service/registry/WMI) persistence techniques, plus web-layer webshell deployment and stealth strategies
Guide for building web apps with the Ping Orchestration JavaScript SDK (also referred to as the Ping Identity JavaScript SDK, formerly the ForgeRock JavaScript SDK / @forgerock/javascript-sdk; npm packages: `@forgerock/journey-client`, `@forgerock/davinci-client`, `@forgerock/oidc-client`). Use when the user wants to add Ping authentication to a web app — phrases like "add Ping auth to my web app", "use PingOne in React", "set up Journey in JavaScript", "build a Ping login page", "use DaVinci in my SPA", "integrate @forgerock/journey-client", "set up @forgerock/davinci-client", "migrate from @forgerock/javascript-sdk to the new SDK", or "add OIDC login to my React app". Detects framework (React active; Angular, Vue, vanilla JS on the roadmap), collects shared config, delegates Journey to ping-orchestration-reactjs-journey-sdk and DaVinci to ping-orchestration-reactjs-davinci-sdk, and handles OIDC centralized login inline. Covers both new sample app creation and integrating into an existing project.
Generate a full security-focused PRD (Product Requirements Document) from a plain-language feature description. Use this skill whenever someone wants to create a PRD, product spec, feature spec, requirements document, or says things like "write a PRD for", "create a spec for", "plan this feature", "document this feature", or "I need a requirements doc". The skill produces: (1) a structured PRD in a security-focused template format, (2) a Confluence page pushed to your configured space via Atlassian MCP (called directly), (3) a cursor-compatible .md plan file for .cursor/plans/, (4) a downloadable formatted markdown, (5) optionally: Linear/Asana tasks from the batch plan, Slack notification to stakeholders, Notion page mirror. Always use this skill for PRD and feature planning tasks.
Primary entry point for AI model analysis (router): identify the input type—model files go to file-level reverse engineering (re-ai-model), API-only access goes to behavioral evaluation (re-ai-attack), and malicious behavior goes to malware analysis. Trigger terms: AI model analysis, AI model security, model files, model leaks, model reverse engineering, AI model analysis entry point.
ARM architecture reverse engineering (non-Android): Cortex-M/A vector tables, Thumb/ARM switching, AAPCS calling convention, position-dependent code relocation, and MMIO peripheral register cross-referencing. Trigger terms: ARM, arm32, Cortex-M, Cortex-A, Thumb, AAPCS, embedded reverse engineering, bare-metal firmware, stm32, vector table.
eBPF program reverse engineering and adversarial analysis: BPF-64 instruction set, progs/maps relationships, bpftool disassembly, and three use cases: tracing and forensics, malware samples, and EDR evasion. Trigger terms: eBPF, BPF, bpftool, bcc, libbpf, xlated, BPF instructions, bpf hook, EDR evasion, tracepoint, kprobe.
MIPS architecture reverse engineering and router firmware analysis methodology: delay slots, $gp calling convention, endianness determination, and httpd identification. Triggers: MIPS, mipsel, router firmware, embedded, delay slots, big-endian, big-endian, little-endian, httpd, busybox
Publish the user's own gbrain over MCP so other devices, desktop apps and cloud agents can reach it. `gbrain mcp expose` installs and signs in Tailscale, publishes the running `gbrain serve --http` on the tailnet (HTTPS, tailnet-only by default; Funnel only when a client lives in a vendor cloud), keeps the server alive as a user service, and hands back the MCP URL. Then register one least-privilege client per consumer, choose native OAuth/PKCE or a private machine handoff for that client, and verify the connection inside the intended harness.
Reverse engineer Xamarin and .NET MAUI mobile apps by extracting assemblies.blob and XALZ-compressed DLLs with pyxamstore, then decompiling with dnSpy or ILSpy. Use when an APK contains libmonodroid.so, libmonosgen, assemblies.blob, assemblies/*.dll, or libxamarin-app.so, when an IPA contains Mono assemblies, or when jadx shows only Xamarin bootstrap classes.
Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on "parse sarif", "read scan results", "aggregate findings", "deduplicate alerts", or "process sarif output". Handles filtering, deduplication, format conversion, and CI/CD integration of SARIF data. Does NOT run scans — use the Semgrep or CodeQL skills for that.
Use when surveying documented security prior art for a product BEFORE it is built — deriving a threat-vocabulary map (translating a product's surfaces into the terms security corpora index), executing one search angle across weakness and attack-pattern taxonomies (CWE, CAPEC, ATT&CK), vulnerability registries (CVE/NVD, OSV, GitHub Advisory), exploitation-evidence catalogs (KEV, EPSS, Exploit-DB), vendor advisories (CSAF/VEX), incident corpora (VERIS) and control standards (OWASP ASVS, Top 10, MASVS) — or deep-reading ONE source item into an extraction whose evidence tier carries its receipts. Produces schema-validated artifacts with status-typed coverage records and mandatory zero-hit cells. Keywords: security prior art, threat research, vulnerability survey, attack patterns, CVE, CWE, CAPEC, OWASP, KEV, EPSS, advisories, supply chain. Covers the SEARCH, EXTRACT and SYNTHESIS waves.
Shellcode Loader combination generation: select and combine storage/allocator/copier/executor components from the knowledge base to generate a C/C++/Rust Loader. Use when you already have shellcode and need to generate a Loader binary that runs in the target environment. First read references/loader-scenarios.json to confirm no duplicate scenario exists, then choose a combination of the 4 components to generate
Deep subdomain mining with multi-source joint enumeration. Use when you need to maximize subdomain discovery coverage, regular DNS enumeration results are insufficient, or the target uses CDN/wildcard DNS. Cross-discovers via three combined methods: DNS brute force, OSINT engines, and crawling
Passive subdomain enumeration with subfinder. Use when subdomains of a target domain need to be discovered or the attack surface expanded. subfinder is a passive subdomain discovery tool from ProjectDiscovery that aggregates multiple data sources such as Shodan, Censys, SecurityTrails, and VirusTotal; it is fast and stealthy. Use this skill for any scenario involving subdomain enumeration, attack surface discovery, or passive information gathering
Implement OTP Input controls in .NET MAUI applications for authentication flows. Covers input types (Number, Text, Password), styling modes (Outlined, Filled, Underlined), event handling, value binding, validation patterns, and accessibility. Use this skill when building SMS/email OTP verification, multi-step authentication, or secure login forms.
Configure and troubleshoot Teleport auto-discovery for AWS EC2 instances, AWS EKS clusters, and Azure VMs via the Teleport discovery Terraform module. Use to set up or extend auto-discovery, add a region, tag, or subscription, apply the discovery Terraform, check enrollment status, or diagnose why cloud resources are not enrolling. Not for GCP, AWS RDS or database discovery, static or manual join-token enrollment, or Teleport configuration unrelated to discovery.
Test Industrial Control Systems and Operational Technology protocols—Modbus, DNP3, OPC UA, BACnet, EtherNet/IP, S7comm, and MQTT—with a safety-first methodology for SCADA and ICS environments. Use when assessing OT network security, testing ICS protocol authentication, reviewing IT-OT segmentation, or conducting authorized ICS penetration tests.
Test mobile inter-process communication and deep link attack surface — exported Android activities, services, receivers and content providers, intent redirection, PendingIntent hijacking, App Links verification, iOS custom URL schemes, Universal Links, and App Groups — using drozer, adb, and Frida. Use when reviewing AndroidManifest.xml exported components, testing deeplinks or URL schemes, or assessing what another app on the device can reach.
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.