Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Web crawling and URL discovery with katana. Use when you need to crawl all pages and endpoints of a target site, discover hidden API paths, endpoints in JavaScript, or extract forms. katana is a next-generation crawling framework from ProjectDiscovery that supports standard mode and headless browser mode and can parse JavaScript to discover dynamic endpoints. This skill should be used for any scenario involving web crawling, URL discovery, JS endpoint extraction, form discovery, or sitemaps
Navigate security work by MITRE ATT&CK tactic and technique — resolve a technique ID or name to the right skill, map a threat intel report or adversary emulation plan to procedures, and run the purple-team loop from technique to detection to validation. Use when a request names an ATT&CK ID like T1003.001, a tactic like lateral movement, an APT group or intel report, or when planning coverage against the matrix.
Use when turning security findings into a clear, actionable report — scoring severity with CVSS, writing findings with reproduction and impact, prioritizing remediation, producing an executive summary, and tracking retests to closure. The phase that makes testing matter.
Uses PyMISP (the official MISP REST API library) to create events with structured IOCs (IPs, domains, hashes, URLs), enrich them with MITRE ATT&CK tags and galaxy clusters, manage sharing groups and distribution levels, search existing intelligence, and export in STIX 2.1 format. Use when creating, enriching, or sharing threat intelligence events on a MISP instance, or integrating IOC feeds with other platforms.
Conducts a sector-specific threat landscape assessment (financial, healthcare, energy, government, etc.) by profiling targeting threat actors, mapping attack vectors and MITRE ATT&CK TTPs with the attackcti/pandas Python stack, and analyzing exploited CVEs and incident trends from ISAC and vendor reports. Use when producing CTI for risk management or board-level reporting on an industry's threat exposure.
Full Windows post-exploitation workflow. Use after obtaining a Windows shell via RCE/webshell/RDP. Covers system information gathering, UAC bypass, local privilege escalation, credential extraction (SAM/LSASS/browsers), and domain reconnaissance. Applies to standalone hosts and domain environments.
Active full-lifecycle asset reconnaissance. Use when you need complete reconnaissance from zero to vulnerability discovery against a target, the first phase of a penetration test, or a comprehensive understanding of the target's attack surface. Covers the full chain of subdomain enumeration → port scanning → liveness detection → fingerprinting → POC scanning.
Guides authorized reverse engineering—static and dynamic binary analysis, disassembly and decompilation workflows, protocol and file-format reversing, defensive malware analysis (behavior, IOCs, YARA ideas), firmware RE, patch diffing, and vulnerability research documentation. Emphasizes written authorization, export-control awareness, and no assistance bypassing protections on unowned or unlicensed software. Use for reverse engineering, disassemble, decompile, Ghidra/IDA-style workflows, binary analysis, malware analysis for defense, firmware RE, patch analysis—not disk imaging forensics (digital-forensics-analyst), live incident command (incident-responder), SOC alert triage (soc-analyst), authorized pentest exploitation (penetration-tester), LLM red team (ai-redteam), or CI pipeline gates (devsecops).
Walk a SubImage attack path step by step, identify the most sensitive impacted assets, propose the fastest remediation, hunt for credible n+1 extensions the engine has not yet modeled, and optionally simulate what-if scenarios. Use when the user asks to “review this attack path”, “explain this attack path”, “what would happen if X is compromised”, “what attack paths involve <asset>”, “find lateral movement opportunities from <asset>”, “assess the blast radius of <asset>”, or pivots from `subimage-mcp:investigate-cve`. Three entry modes: by path id, by asset id, or n+1 extension hunt.
Perform a security review of a diff, branch, or pull request, assessing what the change introduces, weakens, or exposes, with a triage-first workflow and false-positive discipline. Use when asked to security review a PR or branch, check a diff before merge or commit, or assess whether a change is safe to ship
Assess and harden LLM applications and agentic systems against prompt injection, tool misuse, excessive agency, memory poisoning, RAG data leakage, and model supply-chain risk, mapped to the OWASP Top 10 for LLM and Agentic Applications. Use when reviewing an AI feature, agent, MCP server, or RAG pipeline for security, or when threat modeling an autonomous system.
Simultaneous Launch Button - Two-person rule for destructive commands in multi-agent workflows. Risk-tiered classification, command hash binding, 5 execution gates, client-side execution with environment inheritance. Go CLI.
Iterative playbook for bringing Node and TypeScript projects (NestJS + React in a monorepo) to compliance with SonarQube Quality Gates without breaking the build or pipelines. Use when you need to raise coverage by prioritizing New Code, eliminate new issues (Bugs, Vulnerabilities, Code Smells), review Security Hotspots, and control duplication and technical debt.
Deep expertise in securing Supabase applications. Covers Row Level Security (RLS) patterns, auth token validation, storage security, multi-tenant isolation. Use when "supabase security, rls policy, row level security, service role key, multi-tenant rls, supabase, security, rls, postgres" mentioned.
Generates a minimalist interactive HTML “TDIR Security Operations Weekly Report,” readable in 5 minutes or less, with support for ALL, 5 major source domains, and operations-work tabs. Covers the data funnel, timeliness and quality, rule and intelligence status and changes, ticket closure, and endpoint compromise attribution. Does not handle in-depth forensics on individual insights or security incident response.
Use when reviewing who can access which resources in a Teleport cluster, or whether that access is actually used — access list / ACL recertification, "who can reach this database/server", "what can this user access", attesting access for audit/compliance, and finding dormant or unused standing privileges. Covers `tctl access-review`, the `access_path` SQL query language, output semantics, and combining it with `tctl investigate`.
Memory safety, thread safety, concurrency, and critical detection patterns for workerd code review. Covers V8/KJ boundary hazards, lifetime management, cross-thread safety, and coroutine pitfalls. Load this skill when reviewing any C++ code.
Use when a project needs admin/CMS/back-office UI architecture: roles, permissions, content workflows, AI assistant boundaries, audit logs, destructive-action confirmations, and builder handoff. Planning only; do not perform production admin actions or expose secrets.
Analyze packet captures and network telemetry for evidence of intrusion—including capture and handling, the Wireshark/tshark triage funnel, Zeek log mining, Suricata rule runs, beacon and DNS-tunnel detection, TLS/JA3 fingerprinting, HTTP and file carving, exfiltration hunting, and IOC handoff. Use when a `.pcap` or `.pcapng` capture appears, a suspected C2 beacon needs confirmation, data exfiltration needs investigation, malware network behavior must be characterized from its emissions, a Zeek or Suricata alert needs investigation, or DNS tunneling or unusual TLS is suspected.
Reverse engineer Rust binaries — demangling legacy and v0 symbol schemes, recognizing monomorphized generics, Result and Option control flow, trait object vtable dispatch, and panic-site strings that leak source paths and crate names. Use when a binary contains rustc version strings, core::panicking, or _ZN/_R mangled symbols, when a stripped binary is unexpectedly large, or when analyzing Rust malware or a Rust service.
Analyze raw shellcode and position-independent code: extract bytes, guess the architecture, disassemble at the right base, decode self-decoder stubs, resolve hashed Windows APIs, emulate execution to reach the decoded stage, and extract C2 and stage IOCs. Use when handed a raw blob of position-independent code, an extracted payload with no PE/ELF header, shellcode lifted from an exploit or a macro/loader, a `\x`-escaped or base64 buffer, a suspected Cobalt Strike or Metasploit stager, or an egg-hunter
Build and debug encrypted Solana applications with Arcium — data stays private during computation, no single party sees it. Use when writing Arcis circuits (#[encrypted], #[instruction]), wiring Anchor programs with init/queue_computation/callback flows, choosing Shared vs Mxe encrypted state, encrypting inputs with @arcium-hq/client (RescueCipher, x25519), or debugging ArgBuilder ordering, nonce, callback, or computation finalization failures. Covers dark pools, sealed-bid auctions, encrypted voting, hidden game state, confidential DeFi, secure randomness, and threshold signing. Also use for getting started with your first Arcium app.
Audit Model Context Protocol servers for injection surfaces, excessive tool scope, authorization gaps, resource over-exposure, and transport weaknesses across stdio, SSE, and Streamable HTTP deployments. Use when reviewing an MCP server implementation, assessing tool definitions for injection or description manipulation risk, auditing the trust boundary between an AI agent and MCP tools, or reviewing MCP server deployment for authentication and authorization controls.
Use BloodHound.py for Active Directory information gathering. Use when enumerating domain users, groups, computers, sessions, ACLs, and trust relationships, or analyzing in-domain attack paths. BloodHound.py is the Python collector for BloodHound; it gathers AD data over LDAP/DNS/Kerberos and outputs JSON for analysis in the BloodHound GUI. This skill should be used in any scenario involving domain penetration, AD enumeration, or attack path analysis
Static analysis of UEFI/BIOS firmware dumps using Intel's chipsec framework. Decode firmware structure, detect known malware and rootkits (LoJax, ThinkPwn, HackingTeam, MosaicRegressor), generate EFI executable inventories with hashes, extract NVRAM variables, and parse SPI flash descriptors. Use when analyzing firmware .bin/.rom/.fd/.cap files offline without requiring hardware access.
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.