Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Safely analyze, disassemble, decompile, or debug unknown binaries, executables, DLLs, malware, firmware, and packed or obfuscated code. Use for reverse engineering, suspicious-file triage, unpacking, Ghidra/IDA/radare2/x64dbg/GDB help, IOC extraction, YARA, or questions about what a binary does.
Comprehensive Solidity smart contract security auditing and vulnerability analysis skill. Based on methodologies from Trail of Bits, OpenZeppelin, Consensys Diligence, Sherlock, CertiK, Cyfrin, Spearbit, Halborn, and other leading Web3 security firms. This skill should be used whenever the user asks to "audit a smart contract", "review Solidity code for security", "find vulnerabilities", "check for reentrancy", "analyze gas optimization", "review access control", "check proxy patterns", "analyze DeFi protocol security", "review ERC20/ERC721 implementation", "check oracle manipulation risks", "review upgrade patterns", or mentions any security review of EVM-compatible smart contracts. Also triggers for keywords like "slither", "echidna", "foundry fuzz", "formal verification", "invariant testing", "flash loan attack", "MEV", "sandwich attack", "front-running", "delegatecall", "selfdestruct", "reentrancy guard", "access control vulnerability", "storage collision", "proxy upgrade security", "smart contract exploit", "L2 security", "cross-chain", "bridge security", "sequencer", "LayerZero", "CCIP", "account abstraction", "ERC-4337", "smart account", "paymaster", "bundler", "UserOperation", "re-audit", "diff audit", "remediation review", "fix verification", "Uniswap v4 hooks", "Chainlink integration", "Aave integration", "flash loan receiver", "ERC-4626 vault", "restaking", "EigenLayer", "AVS", "severity classification", "severity decision", "perpetual", "perp dex", "GMX", "Synthetix", "funding rate", "liquidation cascade", "intent protocol", "UniswapX", "Permit2", "1inch Fusion", "Dutch auction order", "ZK-VM", "zkSync", "Polygon zkEVM", "ZK proof", "Risc0", "SP1", "Circom", "under-constrained", "ERC-7683", "cross-chain intents", "IOriginSettler", "IDestinationSettler", "CrossChainOrder", "filler protocol", "origin settler", "destination settler", "orderId", "fillDeadline", "EIP-7002", "triggerable exit", "execution layer withdrawal", "validator exit", "EIP-7251", "MaxEB", "max effective balance", "validator consolidation", "consolidation", "EIP-6110", "beacon deposit", "validator deposit", "liquid staking security", "OWASP SC", "OWASP smart contract", "SC01", "SC02", "ERC-6909", "multi-token", "PoolManager claims", "claim token", "isOperator", "MEV bot", "MEV contract", "arbitrage bot", "sandwich bot", "sweep function", "AI-generated code", "Copilot", "vibe coding", "LLM-generated Solidity", "Wake", "eth-wake", "Ackee Blockchain", "TSTORE", "TLOAD", "transient storage", "tstore compiler bug", "tstore poison", "solc 0.8.28", "solc via-ir", "via-ir optimizer", "reentrancy guard bypass tstore", "EOF", "EIP-7692", "Fusaka upgrade", "EXTDELEGATECALL", "EVM object format", "gas observability", "code observability", "CODESIZE EXTCODESIZE EOF", "ERC-7726", "price adapter", "price oracle adapter", "false validity assumption", "IQuote", "getQuote oracle", "phantom collateral", "orphaned state", "Abracadabra exploit", "cook batch router", "failed external call state", "liquidation ghost debt", "overflow sentinel", "Cetus exploit", "bit-shift guard", "FullMath overflow", "PRBMath overflow", "custom math library overflow", "OpenZeppelin v5 migration", "OZ v4 to v5", "ERC-7201 namespaced storage", "sequential storage layout", "namespaced storage layout", "storage slot migration", "LDF rounding", "Bunni exploit", "liquidity distribution function", "asymmetric rounding liquidity", "flash tick shift", "JIT liquidity attack", "just-in-time liquidity", "V4 JIT", "Morpho Blue", "Euler V2", "EVC", "modular lending", "permissionless market", "EigenVault", "cross-vault health", "ERC-4337 executor vault", "EIP-7701", "native account abstraction", "ACCEPT_ROLE opcode", "per-transaction validation", "legacy contract validation", "Cork Protocol", "V4 hook drain", "onlyPoolManager hook", "missing onlyPoolManager", "TransientStorageClearingHelperCollision", "delete transient storage", "delete tstore bug", "ERC-7579 module poisoning", "module onUninstall revert", "stale module state", "executor delegatecall module", "ERC-7484", "module registry attestation", "ERC-7821", "minimal batch executor", "EIP-7821", "sweeper delegation campaign", "tx.origin bypass Pectra", "EIP-7702 sweeper", "cross-chain sandwich", "source chain event leakage", "CeDeFi", "recursive leverage collapse", "oracle price hardcoding", "hardcoded collateral price", "cook() flag bypass", "batch router flag reset", "deferred solvency check bypass", "oracle chain complexity", "restaking oracle chain", "chained price adapter", "Hyperliquid exploit", "vault liquidation absorber", "HLP vault manipulation", "Fusaka gas cap", "EIP-7825", "per-transaction gas limit", "app chain fork", "Berachain fork", "forked L1 inherited bugs", "Aderyn v0.6", "Aderyn LSP server", "echidna verification mode", "halmos recon reproducer", "slither triage", "too many slither findings", "slither false positive", "slither 200 findings", "slither filter", "slither config", "slither suppress", "slither FP", "slither findings triage", "slither-check-upgradeability", "slither priority", "when to skip slither finding", "Solidity 0.9.0", "transfer deprecated", "send deprecated solidity", "transfer removed 0.9", "send removed 0.9", "migrate from transfer call", "PUSH0 cross-chain", "PUSH0 opcode incompatible", "evm-version paris", "evmVersion paris", "shanghai fork compatibility", "non-shanghai chain", "PUSH0 zkSync", "EIP-3855", "ERC-1967 slot corruption", "proxy storage slot", "implementation slot overwrite", "UUPS brick attack", "upgradeTo interface check", "proxiableUUID missing", "storage layout migration", "proxy slot collision", "delegatecall slot overwrite", "ePBS", "EIP-7732", "enshrined PBS", "proposer builder separation consensus", "block access lists", "Block Access Lists", "BALs EIP-7928", "EIP-7928", "Glamsterdam", "payload withholding attack", "preconfirmation timing", "preconf security", "AI-generated code audit", "vibe coding security", "LLM contract review", "copilot Solidity", "hallucinated interface", "broken reentrancy guard AI", "incomplete access control AI", "Noir circuit", "unconstrained Noir", "pub input Noir", "Noir language audit", "SP1 zkVM", "SP1 Succinct", "SP1 cycle limit", "SP1 precompile security", "Polygon CDK", "CDK chain audit", "LxLy bridge", "AggLayer security", "folding scheme", "Nova IVC", "SuperNova folding", "HyperNova", "ProtoStar IVC", "dYdX v4", "dYdX Cosmos chain", "CLOB trust model", "CometBFT MEV", "Gains Network", "gTrade", "DAI vault counterparty", "synthetic perp solvency", "skew manipulation funding", "funding rate oracle", "insurance fund drain", "cross-margin contagion", "isolated to cross margin switch", "xUSD exploit", "Stream Finance exploit", "hardcoded oracle dollar", "Hyperliquid HLP exploit", "HLP liquidation absorber", "dual role vault", "RWA protocol", "real world asset", "tokenized asset", "NAV manipulation", "pool manager trust", "senior tranche", "junior tranche", "epoch redemption", "KYC transfer restriction", "ERC-1400", "ERC-3643", "Centrifuge audit", "Maple Finance audit", "Goldfinch audit", "TrueFi audit", "options protocol", "options settlement oracle", "implied volatility manipulation", "IV oracle", "options expiry manipulation", "covered call vault", "put selling vault", "Ribbon Finance audit", "Dopex audit", "Lyra audit", "Opyn audit", "Hegic audit", "option strike manipulation", "Premia audit", "Aevo audit", "Thetanuts audit", "options-protocols.md", "oToken", "theta vault", "SSOV", "option collateral", "option margin", "option settlement", "call spread payoff", "IV drainage", "Deus DAO oracle", "Gnosis Auction abuse", "prediction market", "prediction market oracle", "resolver manipulation", "conditional token", "CTF conditional", "Gnosis CTF", "LMSR AMM", "market resolution bribe", "Polymarket audit", "Gnosis Safe module", "Safe module audit", "Safe guard", "Safe fallback handler", "enableModule security", "Safe storage collision", "delegatecall Safe", "Zodiac module", "Safe recovery module", "social recovery Safe", "module threshold bypass", "BNB Chain bridge exploit", "BSC bridge Merkle proof", "iavl library bug", "forged Merkle proof bridge", "Multichain exploit", "MPC key centralization", "TSS bridge centralization", "MPC bridge audit", "bridge operator jurisdiction", "single point of failure bridge", "MPC key rotation", "off-chain proof library audit", "ICS23 proof verification", "cross-chain proof forgery", "Code4rena", "C4 contest", "Sherlock contest", "Immunefi", "Cantina contest", "CodeHawks", "Cyfrin Updraft", "warden submission", "Watson submission", "bug bounty submission", "audit contest", "audit competition", "contest finding", "submit to contest", "contest report", "H/M finding", "QA report warden", "vm.signDelegation", "vm.attachDelegation", "vm.signAndAttachDelegation", "ERC-7702 Foundry", "ERC-7702 PoC", "delegation revocation", "forge build --eof", "forge test --eof", "EOF PoC", "EOF migration", "EXTDELEGATECALL proxy", "selfdestruct EOF", "EOF container validation", "Move language", "Move audit", "Sui audit", "Aptos audit", "Move resource", "Sui object model", "Aptos fungible asset", "MoveBit", "OtterSec Move", "hot potato Move", "capability token Move", "Sui PTB", "Move bytecode verifier". Even if the user simply pastes Solidity code and asks "is this safe?" or "any issues here?", use this skill.
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.
Use this skill when the user asks to “analyze network traffic with Wireshark,” “capture packets for troubleshooting,” “filter PCAP files,” “follow TCP/UDP streams,” “detect network anomalies,” “investigate suspicious traffic,” or “perform protocol analysis.” It provides comprehensive techniques for network packet capture, filtering, and analysis using Wireshark.
Use this skill to gate TanStack Start plus TypeScript web-app changes with a pass/fail adversarial review — a single blind reviewer subagent judges a diff or file set against 22 decidable rules covering client/server boundary leaks, server-function and server-route usage, auth and security, SSR data loading, boundary type safety, and compiler config. Trigger it before merging TanStack Start work, when asked to gate, adversarially review, or pass/fail a Start or TanStack codebase, or as a final check on agent-authored Start features. It renders verdicts only and never fixes the work; for teaching-style review feedback use a distillation skill instead.
Audits host firewall state and network-edge exposure on Linux hosts — listener inventory and wildcard bindings, nftables/iptables/ufw/firewalld default-deny design, egress filtering, IPv6 parity, L4 rate limiting, admin-plane isolation, Docker NAT bypass, and cloud security-group reconciliation — with read-only evidence commands and hardened reference rulesets
Review application source code for broken authorization — IDOR / Broken Object Level Authorization (OWASP API1), Broken Function Level Authorization (API5), mass assignment (API3), multi-tenant isolation gaps, and privilege escalation. Reads routes, controllers, resolvers, and data models offline and reports the missing ownership/role check at file:line with a framework-correct fix. No running app, no credentials, no tools. Trigger when reviewing endpoints/handlers, auditing a PR diff that adds or changes routes, hardening a multi-tenant SaaS, or when the user asks "is this endpoint authorized?", "can a user access another user's data?", "IDOR", "BOLA", or "broken access control".
Guides PHP project upgrades using Composer commands. Use when helping users upgrade PHP packages, check for security vulnerabilities with `composer audit`, prioritize which packages to upgrade first, understand dependency conflicts, interpret `composer outdated` output, use `composer why-not` to diagnose version constraints, use `composer why` to trace dependencies, use `composer bump` to harden version constraints after upgrading, plan safe upgrade paths, resolve package version conflicts in composer.json, or resolve merge conflicts in composer.lock. Trigger this skill whenever the user mentions composer packages, PHP dependencies, outdated packages, CVEs in PHP projects, or security advisories.
Cursor-native offensive security engagement and exploitability autoresearch orchestrator inspired by offensive-claude. Use for an authorized offensive engagement, red-team or pentest workflow, Kill Chain style assessment, scoped web/network/cloud/mobile/AD/bug-bounty offensive plan, or exploitability validation of defensive findings. In validate-findings mode it runs a bounded, user-controlled autoresearch loop over deduplicated findings: several hypothesis passes / cycles of hypothesize, experiment, observe, refine. Use it whenever the user asks to run an autoresearch loop, an iterative or multi-pass hypothesis loop, or to loop or iterate over findings for a set number of cycles. Supports engagement mode and validate-findings mode. Instruction-only: ships no scanners, exploit runners, payload builders, or local scripts.
Reduces container attack surface by building application images on Google distroless base images that ship only the application runtime - no shell, package manager, or OS utilities - using multi-stage build patterns plus debugging and scanning techniques adapted to distroless. Use when hardening container images, cutting attack surface in a container architecture, or answering an assessment finding about bloated base images. Keywords: distroless, multi-stage build, no shell, nonroot tag, debug image, scratch, attack surface. Do not use for scanning an image for known CVEs - use scanning-docker-images-with-trivy.
Professional malware analysis workflow for PE executables and suspicious files. Triggers on file uploads with requests like "analyze this malware", "analyze this sample", "what does this executable do", "check this file for malware", or any request to examine suspicious files. Performs static analysis, threat intelligence triage, behavioral inference, and produces analyst-grade reports with reasoned conclusions.
PHP web source expression injection (non-template) audit tool. Identifies user-controllable expression strings entering an expression engine for evaluation/compilation that ultimately lead to sensitive semantic execution, and outputs exploitability grading, PoC and remediation advice (omission prohibited).
PHP filesystem operation audit tool. Focuses on the security risks of operations such as mkdir/chmod/chown/unlink/rmdir/link/symlink/readlink/touch/permissions and TOCTOU, providing "exploitability enhancement evidence" for path validation bypass and write-chain exploitation (does not replace sink sub-audits such as FILE/UPLOAD/WRITE).
PHP web source template injection/SSTI audit tool. Identifies template engine render points and the controllability of template names/expressions, traces to eval/execution chains, and outputs exploitability grading, PoC and remediation advice (omission prohibited).
Execute, inspect, and rerun an existing Promptfoo redteam scan. Use for generated YAML, result exports, attack success rates, grader/target errors, filtered reruns, and CI gates. Use promptfoo-provider-setup for connections and promptfoo-redteam-setup for new scan plans.
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
Triage supplied or imported security findings against a repository using its security policy and static code evidence. Accepts scanner reports, advisories, GitHub findings, and Jira or Linear tickets. Do not use for discovery, duplicate triage, runtime validation, or fixes.
Code-quality gate and coding guardrail for AI coding agents. Always invoke when you finish editing and prepare to hand control back, even if the user did not explicitly ask. Trigger on commit, push, PR, or phrases like any slop, remove slop, review my code, run aislop, or score my code. Scans with aislop, fixes what is mechanical, addresses the rest in-session in the project style, then reports what changed
Backend security review and hardening for authentication, authorization, tokens, sessions, secrets, validation, injection, payments, uploads, webhooks, data exposure, rate limits, and deployment configuration. Use when asked to audit, security-review, harden, threat-check, or inspect backend code for vulnerabilities across Express, NestJS, Django, Rails, Go, and other stacks.
Detect data exfiltration via DNS tunneling (tools like iodine, dnscat2, dns2tcp) by analyzing query entropy, subdomain length, query volume to single domains, TXT/CNAME/NULL record abuse, and oversized response payloads using passive DNS monitoring and statistical/ML methods. Use when hunting for covert DNS-based data exfiltration or building a passive DNS anomaly detection capability.
Microsoft Entra Agent ID (preview) for creating OAuth2-capable AI agent identities via Microsoft Graph beta API. Covers Agent Identity Blueprints, BlueprintPrincipals, Agent Identities, required permissions, sponsors, and Workload Identity Federation. Includes Microsoft Entra SDK for AgentID (containerized sidecar) for polyglot agent authentication (Docker/Kubernetes), 3P agent integration, autonomous and interactive agent patterns. Triggers: "agent identity", "agent id", "Agent Identity Blueprint", "BlueprintPrincipal", "entra agent", "agent identity provisioning", "Graph agent identity", "entra sidecar", "agent id sidecar", "auth sidecar", "3P agent", "third-party agent identity", "polyglot agent auth".
Managing secrets (API keys, database credentials, certificates) with Vault, cloud providers, and Kubernetes. Use when storing sensitive data, rotating credentials, syncing secrets to Kubernetes, implementing dynamic secrets, or scanning code for leaked secrets.
This skill should be used when the user asks to run isolated or untrusted code on Modal.com. PROACTIVELY activate for: modal.Sandbox, safe user code execution, coding playgrounds, named sandboxes, PTY sessions, filesystem snapshots, timeout and resource limits, egress policies, sandbox lifecycle cleanup, terminate(), and security review for code execution. Provides: sandbox security checklist, lifecycle and cleanup patterns, egress/resource-limit recipes, and snapshot/PTY usage examples.
Web application logic mapper for spidering, crawling, hidden API discovery, workflow mapping, state-machine analysis, route relationships, and handoff targets for authz, business logic, XSS, input/protocol, OOB, CVE, exploit, or reporting workflows.
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.