Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Receive and handle Mollie webhooks. Use when setting up Mollie webhook handlers, verifying the X-Mollie-Signature header on next-gen webhooks, or handling payment status changes like paid, expired, failed, canceled, or authorized. Covers both systems: classic webhooks (unsigned, id-only, confirm by fetching the payment from the API) and next-gen webhooks (signed JSON events, HMAC-SHA256 of the raw body).
An NTLM relay attack methodology. Use when the target network has NTLM authentication, SMB/HTTP authentication requests can be triggered, or a NetNTLM Hash is obtained. Covers Responder poisoning, ntlmrelayx relaying, printer bug forced authentication, RBCD relaying, Shadow Credentials, and ADCS relaying. Use this skill for any scenario involving NTLM, Relay, Responder, or relay attacks
Use when a user asks for help with Ping Identity SDK, ForgeRock SDK, or Ping Orchestration SDK integration without specifying a platform — phrases like "help me add Ping auth", "I want to use PingOne", "get started with the Ping Orchestration SDK", "add Ping login to my app", "integrate the ForgeRock SDK", "use the pingidentity SDK". Probes the project to detect Android, iOS, JavaScript, or React Native, asks if ambiguous, and routes to the matching umbrella skill (ping-orchestration-android-sdk, ping-orchestration-ios-sdk, ping-orchestration-javascript-sdk, ping-orchestration-react-native-sdk) or to forgerock-to-ping-journey-migration when ForgeRock SDK references are present (forgerock-android-sdk, forgerock-ios-sdk, @forgerock/javascript-sdk).
Post Superagent PR security scan findings as inline GitHub pull request review comments using the authenticated gh CLI. Use whenever you need to comment on a PR scan finding, manage Superagent PR labels, complete a GitHub check run, or avoid posting findings as general PR thread comments. Trigger for any Superagent sandbox PR scan handoff that owns GitHub side effects via gh.
Reverse engineer undocumented binary network protocols from packet captures and the client that speaks them — recovering framing and field structure, identifying length prefixes, opcodes, checksums and encryption, and building a Wireshark/Kaitai/scapy parser to replay or fuzz. Use when analyzing a proprietary TCP/UDP protocol, a game or IoT or C2 protocol with no spec, or traffic that Wireshark shows only as raw bytes.
Use when judging a finished security prior-art artifact — a threat-vocabulary map, a per-angle search output, an extract record, or the threat register — to decide whether the research craft is honest, complete against its own contracts, and proportionate. An acceptance gate, not authoring: it runs the producer's validator once, then judges what a validator cannot see — whether a coverage claim is provable, whether a source failure was typed or written as a zero, whether a bail was a confident relevance bail rather than a hedge, whether an evidence tier follows from evidence the record's own body agrees with, and whether a register names threats from a real vocabulary rather than coining them. Emits VERDICT: approve|revise with condition-named findings. Keywords: security prior art review, threat research review, coverage honesty, survey acceptance gate. Judges all three survey waves.
Detect, audit, and remediate Security Misconfiguration vulnerabilities (OWASP A02:2025) in Python web applications — especially FastAPI and Flask. Use this skill whenever a user asks about: hardening a Python/FastAPI/Flask app, checking for debug mode leaks, missing security headers, exposed API docs, hardcoded secrets, insecure cookie flags, XXE vulnerabilities, or any OWASP A02 misconfiguration issue. Also trigger for tasks like "security audit", "pen test prep", "production checklist", "find misconfigs", or "harden my app". This skill covers static analysis patterns, runtime checks, tooling (Bandit, OWASP ZAP), and remediation code snippets for each sub-category of misconfiguration.
Prepare and review security questionnaire responses, trust center answers, vendor risk evidence, enterprise buyer security packets, control mappings, gaps, remediation notes, and truthful sales handoffs. Use when responding to customer security reviews, procurement questionnaires, SSO/audit/data questions, privacy evidence requests, or enterprise trust due diligence.
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
Automated security auditing for AI agent code. Scans repos, packages, MCP servers, and installed skills for malicious patterns using eight-phase analysis: install hooks, dangerous code patterns, network exfiltration, credential access, obfuscation, provenance, prompt injection, and skill security. Use when: cloning repos, installing packages, reviewing MCP servers, auditing skills, scanning code before execution, or when asked to check if something is safe, audit code, scan for malware, review dependencies.
Personnel intelligence gathering and social engineering attack preparation for a target organization. Use when the target's email format, key personnel information, or organizational structure needs to be collected, or when preparing phishing/watering hole attacks/credential guessing. Suited to the social engineering preparation phase of a penetration test
Use this skill when the user asks to "automate SQL injection testing," "enumerate database structure," "extract database credentials using sqlmap," "dump tables and columns from a vulnerable database," or "perform automated database penetration testing." It provides comprehensive guidance for using SQLMap to detect and exploit SQL injection vulnerabilities.
Holistic target profiling and attack surface analysis. Use when target assets need to be systematically organized, a structured target profile needs to be generated, or target information needs to be shared in a multi-person penetration test. Focuses on analysis and reporting rather than scanning itself. Suited to in-depth analysis of data after recon-full
Design and audit admin settings information architecture, workspace controls, role and permission settings, billing/admin separation, security settings, defaults, auditability, dangerous actions, policy inheritance, team management, and enterprise admin UX. Use when building settings for SaaS, developer tools, marketplaces, desktop apps, or multi-user products.
Conducts privacy auditing of AI models including training data extraction testing, membership inference attacks, model inversion testing, and attribute inference assessment. Uses ML Privacy Meter and related tools to quantify privacy leakage. Keywords: model audit, membership inference, privacy meter, model inversion, training data extraction.
Implements AI transparency requirements under EU AI Act Arts. 13-14 and GDPR Arts. 13-14. Covers user notification of AI interaction, system capability disclosure, limitation documentation, and meaningful information about automated logic. Keywords: AI transparency, EU AI Act, GDPR notification, explainability, automated decision.
Reverse engineer and security-review macOS applications and Mach-O binaries — thinning universal binaries, recovering Objective-C/Swift structure, reading code-signing entitlements and the hardened runtime, and auditing XPC services, dylib load paths, and TCC privacy exposure. Use when analyzing a .app bundle or Mach-O on macOS, checking entitlements and notarization, hunting a dylib-hijack or XPC privilege bug, or reasoning about Gatekeeper and quarantine.
Router skill for API penetration testing across REST, GraphQL, gRPC, and WebSocket. Covers OWASP API Top 10 (2023) including BOLA/BFLA/BOPLA, JWT attack chains, GraphQL introspection abuse, and mass assignment. Invoke when the user asks to pentest an API, analyze OpenAPI/Swagger, test auth/authorization, fuzz endpoints, or find API vulnerabilities.
Assess the physical attack surface of embedded devices — finding and using UART consoles, JTAG/SWD debug, and SPI/I2C flash; dumping firmware off-chip; triaging secure boot; and studying sub-GHz RF replay feasibility with an SDR. Use when you have physical access to a device or board, need to identify test pads and get a serial/root shell, want to read a flash chip with flashrom, or are evaluating a fixed- vs rolling-code radio in a shielded lab.
Guides privacy audit sampling methodology including statistical and non-statistical sampling, sample size determination, stratification techniques, attribute sampling for compliance testing, confidence level selection, tolerable deviation rates, and extrapolation of results to the population. Keywords: audit sampling, statistical sampling, attribute testing, sample size, confidence level, stratified sampling, privacy audit.
Manages GDPR Article 22 rights related to solely automated decision-making and profiling, including identification of automated decisions, meaningful human oversight implementation, logic explanation requirements, and contestation mechanisms. Activate for automated decision, profiling, Art. 22, algorithmic decision, AI decision queries.
Manage Backblaze B2 cloud storage. List files, audit usage, estimate cost, clean up stale data, review security posture, and manage lifecycle rules. Use when the user mentions B2, Backblaze, object storage buckets, or storage cleanup.
Production backend systems development. Stack: Node.js/TypeScript, Python, Go, Rust | NestJS, FastAPI, Django, Express | PostgreSQL, MongoDB, Redis. Capabilities: REST/GraphQL/gRPC APIs, OAuth 2.1/JWT auth, OWASP security, microservices, caching, load balancing, Docker/K8s deployment. Actions: design, build, implement, secure, optimize, deploy, test APIs and services. Keywords: API design, REST, GraphQL, gRPC, authentication, OAuth, JWT, RBAC, database, PostgreSQL, MongoDB, Redis, caching, microservices, Docker, Kubernetes, CI/CD, OWASP, security, performance, scalability, NestJS, FastAPI, Express, middleware, rate limiting. Use when: designing APIs, implementing auth/authz, optimizing queries, building microservices, securing endpoints, deploying containers, setting up CI/CD.
End-to-end Chrome security backport for an Electron release branch. Given a Chrome Releases blog URL and a branch (e.g. 41-x-y), determines which CVE fixes are missing from the *actual synced source*, writes the cherry-pick patches locally, validates them with `e sync --3` + `lint --patches`, then pushes a single PR. Use when asked to backport a Chrome security release to N-x-y, "is CVE-X already in N-x-y?", or to produce/validate the cherry-pick set for a release branch.
Use when inspecting or changing anything in a Cloudflare account as an agent — DNS records, WAF custom rules, bot settings, redirect, transform, cache or page rules, zone settings, tunnels, Workers, Pages, R2 or analytics. Reads go through a local read-only API token that the agent never sees. Changes are proposed for the human to make in the dashboard, or applied through an approval step when the user has deliberately stored a write token.
CTF AI/ML attack techniques. Use when challenges involve AI model attacks, adversarial example generation, model extraction, prompt injection/jailbreaking, LoRA weight manipulation, LLM token smuggling, membership inference attacks, training data poisoning, or neural network analysis. Covers the full AI security attack/defense chain: FGSM/PGD/C&W adversarial attacks, model inversion, model weight perturbation and recovery, LLM toolchain hijacking, context window manipulation, and more
Guides compliance with country-specific data localization requirements across key jurisdictions including Russia (242-FZ), China (PIPL Art. 40, CAC measures), India (DPDP Act), Turkey, Vietnam, and Indonesia. Covers localization assessment, architecture design, and exemption procedures. Keywords: data localization, data residency, PIPL, 242-FZ, cross-border restrictions.
Locate the vulnerability a security patch fixes by diffing the pre- and post-patch binaries — using BinDiff, Diaphora, or ghidriff to find the changed functions, reading the added checks to recover the bug class, and reasoning back to a reachable pre-patch trigger for 1-day analysis. Use when comparing two versions of a DLL/ELF, extracting a Microsoft patch from an MSU/MSP for delta comparison, or turning a vague advisory into the exact code that changed.
GDPR-compliant Data Processing Agreement drafting per Article 28(3). Covers all 8 mandatory provisions including subject matter, duration, nature and purpose, data types, categories of data subjects, controller and processor obligations, and sub-processor cascade requirements.
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.