Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Lateral movement techniques. Use when obtained credentials (passwords/hashes/keys/tickets) need to move from the current host to other hosts. Covers SSH, RDP, WMI, PSExec, PTH, PTT, DCOM, and more. Choose the best movement method based on the target operating system and the type of credentials available
Prioritize and drive remediation of a vulnerability backlog by real risk, not raw CVSS — combining severity with exploitation signals (EPSS, CISA KEV), asset exposure and business context, using SSVC-style decisions, distinguishing reachable from merely present, and tracking remediation and exceptions. Use when triaging scanner output, deciding what to patch first, building a risk-based vulnerability management process, or explaining why a critical CVE is not the top priority.
Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — authentication, sessions, rate limiting, input-schema validation, official-SDK usage, RCE vectors, and the OWASP MCP Top 10 — producing a report with file/line evidence. Use this skill when: - Reviewing an MCP server implementation for security before release - Checking a server against the baseline controls (MCP-01 to MCP-05) and the OWASP MCP Top 10 - Auditing tools for RCE vectors (command/code injection, unsafe deserialization, path traversal, SSTI, dependency hijacking, SSRF) - Verifying auth, session, rate-limiting, and input-validation controls on a network-exposed server - Reviewing MCP client code that handles untrusted server responses and session IDs - Requests like "review this MCP server for security" or "is my MCP server implementation secure?"
Use picocom to interact with IoT device UART consoles for pentesting operations including device enumeration, vulnerability discovery, bootloader manipulation, and gaining root shells. Use when the user needs to interact with embedded devices, IoT hardware, or serial consoles.
Crash and vulnerability sample analysis: deterministic reproduction, ASAN/UBSAN report interpretation, input minimization (afl-tmin/cmin), gdb backtrace localization, rr recording and replay, and PoC generation. Trigger terms: crash, ASAN, UBSAN, undefined behavior, UAF, heap overflow, out-of-bounds, segmentation fault, segfault, core dump, PoC, vulnerability analysis, crash analysis.
Electron desktop app reverse engineering: asar unpacking, main/renderer process JS, V8 bytecode (.jsc) boundaries, CDP dynamic debugging, and anti-debugging countermeasures. Triggers: Electron, asar, desktop app reverse engineering, .jsc, V8 snapshot, CDP, ELECTRON_RUN_AS_NODE, devtools detection.
Firmware/embedded/hardware analysis gateway. Workflow: extraction → rootfs → emulation → hardware interfaces. Subskills: [[re-fw-extract]] [[re-fw-rootfs]] [[re-fw-emulate]] [[re-hardware-io]] [[re-automotive]] [[re-uefi]] [[re-rtos]] [[re-tee]]. Trigger terms: firmware analysis, firmware, IoT, unpacking firmware, rootfs, firmware emulation.
Coverage-guided fuzzing: AFL++/libFuzzer/honggfuzz, instrumentation and corpus initialization, afl-fuzz runtime parameters, coverage (afl-cov), dictionaries/structured inputs. Trigger terms: fuzz, fuzzing, AFL, afl-fuzz, libFuzzer, honggfuzz, coverage, corpus, dictionary, vulnerability hunting.
Virtualization reverse engineering: VT-x/SVM, hypervisor detection, VMCS/EPT analysis, and partitioning and vdev semantics in Xen / QNX Hypervisor / Jailhouse / ACRN / Bao / Hyper-V·VMBus / XtratuM / LynxSecure / Quest-V. Trigger terms: hypervisor, VT-x, SVM, virtualization detection, EPT, Xen, grant table, event channel, Jailhouse, cell, ACRN, ivshmem, Bao, shmem_id, vdev, GPA/HPA, Hyper-V, VMBus, VSC, VSP, GPADL, SR-IOV, XtratuM, XM_CF, LynxSecure, Quest-V, sandbox kernel
Managed code reverse-engineering gateway. Orchestration: identify runtime → decompile → deobfuscate → route malware scenarios to [[re-malware]]. Subskills: [[re-dotnet]] [[re-java]] [[re-script-deob]] [[re-wasm]] [[re-ai-triage]] → [[re-ai-model]] [[re-blockchain]] [[re-python]]、[[re-browser-ext]]、[[re-electron]]、[[re-javacard]]. Trigger terms: .NET, dnSpy, ILSpy, Java, jar, bytecode, PowerShell obfuscation, VBA macro, JS deobfuscation, managed code.
Vulnerability hunting gateway. Orchestration: identify targets and input surfaces → coverage-guided fuzzing → crash analysis → reverse-engineering and localization → report. Sub-skills: [[re-fuzzing]] [[re-crash-triage]] [[re-exploit]]. Trigger terms: vulnerability hunting, find vulnerabilities, fuzz, fuzz testing, AFL, libFuzzer, crash analysis, crash, vulnerability hunting, fuzzing
Use this skill when the user asks to “follow red team methodology,” “perform bug bounty hunting,” “automate reconnaissance,” “hunt for XSS vulnerabilities,” “enumerate subdomains,” or needs security researcher techniques and tool configurations from top bug bounty hunters
Firmware extraction and IoT security analysis (RE Level 5) for routers and embedded systems. Use when analyzing IoT firmware, extracting embedded filesystems (SquashFS/JFFS2/CramFS), finding hardcoded credentials, performing CVE scans, or auditing embedded system security. Handles encrypted firmware with known decryption schemes. Completes in 2-8 hours with binwalk+firmadyne+QEMU emulation.
Use when preparing server provisioning plans, IaC drafts, SSH hardening, users, firewalls, backups, monitoring, and rollback. Dry-run by default; do not create, mutate, or destroy production servers without explicit approval.
Use when a public website needs an AI assistant with source-bounded answers, RAG/content scope, injection protection, escalation, logging, rate limits, refusals, and no hallucinated product/legal/price claims. Planning or implementation handoff only; do not expose secrets or give destructive tools.
Use when planning SSL/TLS, HTTPS redirects, HSTS, security headers, CSP, cookie flags, backups, monitoring, and basic launch hardening. Dry-run first; do not mutate production server, DNS, certificates, or secrets without explicit approval.
Work a security alert queue to a defensible disposition — separating true positives from false positives and benign true positives, reasoning about base rates before escalating, ordering enrichment by cheapest discriminator, time-boxing, and documenting negative results so a closed alert is evidence rather than a guess. Use when triaging SOC or EDR alerts, deciding whether an alert warrants incident response, working through an alert backlog, or determining why a detection keeps firing.
Integrate, test, debug, and harden Verify.et transaction verification API implementations. Use when building Verify.et server-side adapters, payment or checkout verification, account webhook registration (dashboard or API), webhook receivers and signing secrets, opt-in receipt image processing (QR or OCR), polling or SSE status flows, API-key auth, idempotency, credits or quota handling, bank-specific payloads, or production error handling.
Decide whether an agent skill, plugin, or MCP server is safe to install into an AI coding agent, where its content is loaded into a model's context and its config can run on startup. Use when reviewing a skill pack, Claude Code / Cursor / Cline plugin, or MCP server before adoption; when a repo ships a SKILL.md, .mcp.json, or plugin.json you are about to trust; or when judging whether third-party agent content can steer the model or exfiltrate an engagement.
Strip multi-vendor AI provenance marks from text and files using the guillaumemeyer/watermarks-remover Python toolkit: invisible Unicode/space homoglyphs (Layer A, deterministic), statistical token-sampling watermarks via agent-guided rewrite (Layer B, best-effort), and C2PA/EXIF/XMP/doc-props metadata on PNG, JPEG, SVG, PDF, DOCX, ODT, HTML, and Markdown. Covers Claude, Gemini/SynthID-Text, OpenAI provenance surfaces, and open-LLM Kirchenbauer-style marks, plus optional external backends for SynthID pixel scoring and CtrlRegen pixel-domain removal. Use when the user wants to strip AI watermarks, remove C2PA / Content Credentials, clean AI metadata from a file, remove invisible Unicode / zero-width characters from AI-generated text, or audit a directory/website for AI provenance signals. Triggers on: "remove watermark", "strip C2PA", "remove AI metadata", "clean invisible unicode", "remove-ai-marks", "SynthID removal", "audit_dir.py", "Layer A / Layer B watermark removal".
Senior defensive web security architecture for creating, editing, auditing, hardening, and monitoring websites, web apps, APIs, SaaS products, ecommerce, dashboards, auth flows, sessions, cookies, browser security headers, CSP, CORS, access control, secrets, dependency and supply-chain security, logging, incident readiness, privacy-sensitive flows, and AI/agent-enabled web features. Use when the user asks about website security, appsec, OWASP, ASVS, Top 10, API security, threat modeling, secure code review, authentication, authorization, session management, CSRF, XSS, SQL/NoSQL injection, SSRF, file upload security, security headers, TLS/HSTS, CSP, CORS, cookies, rate limiting, bot abuse, secrets, dependency scanning, vulnerability remediation, security monitoring, or making a site secure by design.
Author durable YARA detection rules — meta/strings/condition anatomy, string types and modifiers, structural conditions with file magic and offsets, the PE/ELF/math/hash modules, specificity-vs-durability tuning, atom-aware performance, memory and process scanning, and YARA-X. Use when writing a YARA rule, creating a signature for a malware family or a file/memory artifact, turning IOCs or a captured sample into a detection, or hunting for a family across a corpus with Retrohunt or an on-host scanner.
Exploit CI/CD pipeline misconfigurations and OIDC federation weaknesses across GitHub Actions, GitLab CI, and Jenkins—poisoned workflows, secret exfiltration, runner compromise, overly broad OIDC trust policies, build artifact poisoning, and credential theft. Use when pentesting CI/CD infrastructure, assessing OIDC federation trust boundaries, reviewing pipeline security posture, or exploiting a path from repository access to cloud credentials.
Perform dead-disk forensics on an acquired disk image using The Sleuth Kit, Plaso, and bulk_extractor — verify integrity and mount read-only, map partitions, recover deleted files, build a file-system and super-timeline, carve unallocated space, mine registry hives and OS artifacts, and detect anti-forensics. Use when handed a .E01/.dd/.raw/.vmdk/.vhdx disk image or forensic acquisition to examine, recovering deleted files, building a file-system timeline, or carving artifacts from unallocated space.
Systematically identify and analyze persistence mechanisms on Linux systems during DFIR investigations -- sweep systemd units, cron jobs, shell initialization, SSH config, kernel modules, LD_PRELOAD, package manager hooks, udev rules, container entrypoints, and XDG autostart entries. Use when investigating a compromised Linux host, performing forensic analysis of a Linux disk image, looking for backdoors or unauthorized access mechanisms, or determining how an attacker maintained access.
Test GraphQL APIs—introspection and schema recovery when introspection is disabled, field suggestion abuse, batching and alias-based rate limit bypass, query depth and complexity denial of service, authorization gaps per field and per resolver, and mutation abuse. Use when a target exposes /graphql, /v1/graphql, or /api/graphql, when requests contain a query or mutation body, or when responses carry a data and errors envelope.
Test gRPC and Protocol Buffers services—recovering .proto definitions from server reflection or compiled descriptors, calling methods with grpcurl and grpcui, intercepting HTTP/2 and gRPC-Web traffic, and fuzzing unknown message schemas with protobuf-inspector. Use when a target speaks gRPC, HTTP/2 with application/grpc, or when a request body is opaque binary protobuf rather than JSON.
Attack SAML single sign-on by decoding and tampering with signed XML assertions—XML signature wrapping (XSW1-XSW8), signature stripping, assertion and attribute tampering, NameID comment injection, XXE through the SAML parser, certificate faking, recipient confusion and IdP-initiated replay, and Golden SAML forgery. Use when a request carries a `SAMLRequest` or `SAMLResponse` parameter, when base64+deflate decodes to XML with `<saml:Assertion>`, when the target exposes a `/saml/acs` or `/sso` endpoint, when an IdP-initiated login lands an assertion at the SP, or when federation runs through Okta, ADFS, Ping, or Azure/Entra.
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.