Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
CloudBase auth provider configuration and login-readiness guide. This skill should be used when users need to inspect, enable, disable, or configure auth providers, publishable-key prerequisites, login methods, SMS/email sender setup, or other provider-side readiness before implementing a client or backend auth flow.
Use this skill when the user asks to "intercept HTTP traffic", "modify web requests", "use Burp Suite for testing", "perform web vulnerability scanning", "test with Burp Repeater", "analyze HTTP history", or "configure proxy for web testing". It provides comprehensive guidance for using Burp Suite's core features for web application security testing.
Explains what a member or a role can do in a PostHog project, using the access control MCP tools. Use when the user asks what someone can see or edit, who can edit dashboards or feature flags, why a member can or cannot open a dashboard, notebook or table, what a role grants, which properties are hidden from someone, or how the project's default access is set. Covers what each level means, how the stored rule, the enforced level and the inherited access relate, what the null values mean, which tool answers which question, and when the answer needs the role tools too.
Mandatory CTF/range flag verification process. When a suspected flag string (including formats such as flag{, FLAG{, ctf{) is found through **any means**, you **must immediately** use this skill to verify it; do not submit it directly. This prevents submitting an incorrect flag due to character truncation, encoding errors, HTML entities, incomplete base64 decoding, hex truncation, and similar issues. Even if the flag looks complete, hidden characters or encoding problems may be present. Covers all flag extraction scenarios such as segmented extraction via SQL injection, truncated command execution output, file read encoding, and web page parsing. Any time you see the string flag{, this skill should be triggered
Deploys a Software-Defined Perimeter per the CSA v2.0 specification, configuring Single Packet Authorization, mutual TLS, and SDP controller/gateway components to enforce zero trust network access. Use when building or hardening zero trust network architecture, implementing SPA-based "invisible" infrastructure that cloaks services from unauthenticated scanning, or meeting compliance requirements for zero trust network access.
Deploys and operates Falco with the modern eBPF driver in Kubernetes and Docker, covering driver selection, Helm installation, output channels, and the built-in ruleset that detects container escape, namespace abuse, privileged mounts, and anomalous syscalls. Use when standing Falco up on a cluster, choosing between the eBPF and kernel-module drivers, routing Falco alerts into a SIEM or Falcosidekick, or upgrading an existing deployment. Keywords: Falco, modern_ebpf, kernel module, Helm, Falcosidekick, runtime security, syscall. Do not use for authoring individual escape rules - use detecting-container-escape-with-falco-rules.
Production-grade Docker containerization for Python and Node.js applications. This skill should be used when users ask to containerize applications, create Dockerfiles, dockerize projects, or set up Docker Compose. Auto-detects project structure, analyzes .env for secrets, validates security, and generates tested Dockerfiles.
Complete reference for the ffuf fuzzing tool. Used for directory/file discovery, parameter fuzzing, virtual host enumeration, POST data fuzzing, and multi-position fuzzing. Use when you need path brute-forcing, parameter discovery, or subdomain enumeration on web applications. More flexible than gobuster/dirsearch — supports multiple FUZZ positions and custom filtering. Use this skill for any scenario requiring brute-force enumeration of web paths or parameters
Guides a comprehensive organisational data protection audit against key GDPR requirements including Articles 5, 24, 25, 28, 30, 32, 35, and 37. Includes 50+ control points covering principles, accountability, security, and governance. Activate when performing compliance audits, preparing for supervisory authority inspections, or assessing organisational GDPR maturity. Keywords: data protection audit, compliance audit, GDPR audit, control points, accountability.
Detect DCSync attacks (MITRE ATT&CK T1003.006) by analyzing Windows Event ID 4662 (AccessMask 0x100) for DS-Replication-Get-Changes and DS-Replication-Get-Changes-All requests issued by non-domain-controller accounts. Use when hunting for DCSync credential theft, after detecting Mimikatz-class tooling, or during incident response and purple-team exercises involving Active Directory replication abuse.
Hunts for adversary persistence and execution via Windows scheduled tasks (T1053.005) by analyzing Security Event ID 4698 task-creation events, suspicious task properties, and unusual execution patterns from schtasks.exe/at.exe. Use after detecting schtasks or at.exe in process creation logs, during incident response to enumerate persistence on compromised hosts, or when Event ID 4698 fires for an unusual task.
Implements digital signatures using the Ed25519 algorithm (Curve25519), covering key-pair generation, signing, signature verification, and security tradeoffs versus RSA and ECDSA. Use when adding message or artifact signing and authentication-integrity checks to a system, or when advising on Ed25519 key properties and validation criteria.
Queries FIRST's Exploit Prediction Scoring System (EPSS) API to fetch exploitation-probability and percentile scores for CVEs, then uses those scores to prioritize vulnerability remediation. Use when triaging or ranking a vulnerability backlog by real-world 30-day exploitation likelihood rather than CVSS severity alone.
Configures Google Workspace advanced phishing and malware protection settings in the Admin Console — pre-delivery message scanning, attachment protection, spoofing/impersonation detection, and Enhanced Safe Browsing enforcement. Use when hardening Gmail against phishing, spoofing, and malware, or when tuning Workspace email security policies.
Implements the Schnorr identification protocol and a simplified Zero-Knowledge Password Proof (ZKPP) over the discrete logarithm problem, letting a prover authenticate by demonstrating knowledge of a secret without ever revealing it to the server. Use when designing or building password-less or password-secret-free authentication, or when a server must verify a user's credential without learning or storing the underlying secret.
Detect, analyze, and remediate OWASP A06:2025 Insecure Design vulnerabilities in Python web applications (FastAPI and Flask). Use this skill whenever the user asks about architecture-level security flaws, threat modeling, rate limiting gaps, business logic vulnerabilities, insecure file uploads, race conditions, tenant isolation failures, or client-side enforcement of server-side security. Trigger even if the user doesn't say "Insecure Design" explicitly — common signals include: "missing rate limiting", "file upload security", "business logic flaw", "race condition", "multi-tenant isolation", "threat modeling", "STRIDE", "design review", or "can users abuse this flow". Also trigger for code reviews or audits where architecture-level security controls are being evaluated, not just implementation bugs.
Investigate security incidents in Amazon Web Services—reconstruct attacker activity from CloudTrail, VPC Flow Logs, and GuardDuty; anchor the investigation on the compromised principal (access key or role); trace privilege escalation and persistence through IAM API calls; detect data exfiltration and crypto-mining; and contain the incident without destroying evidence or tipping off the attacker. Use when responding to a suspected AWS compromise, exposed access keys, anomalous CloudTrail activity, a GuardDuty finding, unexpected IAM changes, crypto-mining EC2 instances, or S3 data exfiltration.
Investigate a compromised or suspicious Windows host from on-disk artifacts — triage collection, evidence of execution (Prefetch, Amcache, Shimcache, SRUM, UserAssist, BAM), the event-log workhorses by ID (Security 4624/4688/4720/7045/1102, Sysmon, PowerShell 4104, RDP, WMI), persistence hunting across every autostart, lateral-movement traces, $MFT/USN filesystem forensics, anti-forensics detection, and building a super-timeline with the Eric Zimmerman suite, Chainsaw, Hayabusa, and Plaso. Use when triaging a compromised or suspicious Windows host, working through EVTX/Sysmon logs, reconstructing what executed on a Windows machine, hunting persistence and lateral-movement traces, or analyzing a KAPE/triage collection.
Extract hidden API endpoints via JavaScript static analysis. Use when the target is an SPA or a decoupled frontend/backend architecture, when the page uses Vue/React/Angular, or when conventional directory scanning yields little. Extract API paths, keys, internal domains, and WebSocket endpoints by analyzing JS bundles. This is the information-gathering phase of API penetration testing. After finding endpoints → api-fuzz for semantic fuzzing
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
AI-first security scanning with Medusa. 3,000+ detection patterns covering AI/ML, agents, MCP, RAG, prompt injection, and traditional SAST vulnerabilities. Wraps Medusa CLI with SARIF/JSON parsing, structured finding output, OWASP mapping, and remediation guidance.
Multi-layer network penetration and tunneling. Use when you need to pivot from the DMZ to the internal network, penetrate across network segments, or when the target sits behind multiple layers of firewalls or network partitions. Covers proxy setup (frp/chisel/SSH), multi-hop tunnel chains, port forwarding, and SOCKS proxies. The complete multi-layer attack path from perimeter breach to domain controller
Build services on PostgREST-compatible BaaS (Supabase / InsForge) — RLS, Auth, PostgREST queries, MCP settings. This skill MUST be loaded before writing any RLS policy or PostgREST query, and MUST NOT be skipped because the query looks like ordinary SQL. Triggers on: 用 Supabase / InsForge 做後端, 設計 RLS policy, 寫 PostgREST query, 處理 BaaS Auth, 設定 MCP, 推 Supabase production, 自架 Supabase, InsForge.
AI model security assessment and forensics (behavioral layer): extraction assessment (API black-box extraction assessment), fingerprint verification (behavioral fingerprinting and attribution verification), privacy leakage evaluation (membership inference/privacy leakage assessment), and robustness evaluation (adversarial robustness assessment). Triggers: API model theft, black-box model replication, model fingerprinting, membership inference, adversarial examples, behavioral watermarking, model security assessment, privacy leakage assessment.
CTF practice gateway. Orchestration: identify challenge type → simple challenges go directly to [[re-binary-core]] → automation needed [[re-angr]]/[[re-z3]] → obfuscation [[re-deobfuscate]]. Sub-skills: [[re-angr]] [[re-z3]] [[re-pwn]], [[re-stego]]. Triggers: CTF, challenge, reverse-engineering challenge, pwn, babyre, automated solving, symbolic execution, angr, z3, solver, find flag.
Physical-layer hardware reverse engineering: decapsulation, die analysis, probes and FIB, PCB circuit analysis, and hardware Trojan detection. Trigger terms: chip reverse engineering, decapsulation, decapping, PCB, hardware Trojan, circuit analysis, die, FIB, side channel, SPA, DPA, fault injection, clock glitch, voltage glitch
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.