Security
Security agent skills give AI agents disciplined security workflows: code review for vulnerabilities, secret handling, dependency audits, and hardening checklists. Every skill on SkillMD also passes its own safety review before listing, with capability flags shown on each page.
-
aws-samples Skill Generate PreventiveGenerate preventive and proactive security control artifacts — SCPs, resource policies, KMS key policies, permission boundaries, tag policies, OPA policies, and CloudFormation Guard rules. Reads from mapping-results.json and validated.json.
-
aws-samples Skill Map Generate ControlsGenerate security controls from mitigations x capabilities, organized by Category x Scope matrix. Produces map-controls-generated.json with rich metadata for downstream framework mapping. Consumes validated.json.
-
l-gevity Skill Architecture As Code PythonPython implementation of the `architecture-as-code` pattern. Per-package `architecture.toml` files merged into a single `import-linter` config and enforced via `lint-imports` (over a Grimp-built import graph). TRIGGER when: implementing or extending architecture-as-code in a Python repo, debugging an `import-linter` contract, or adapting the assembler. SKIP for routine edits inside a governed package. Reads in conjunction with `architecture-as-code` (the pattern, source of truth for schema, rule placement, anti-patterns, and audit checklist) — this skill defines only the Python-specific encoding, assembler code, and gotchas.
Audited -
l-gevity Skill Architecture As Code JavascriptJavaScript / TypeScript implementation of the `architecture-as-code` pattern. Per-module `eslint.architecture.mjs` files merged into a single ESLint flat-config and enforced via `eslint-plugin-boundaries`. TRIGGER when: implementing or extending architecture-as-code in a JS/TS repo, debugging an `eslint-plugin-boundaries` rule, or adapting the assembler. SKIP for routine edits inside a governed module. Reads in conjunction with `architecture-as-code` (the pattern, source of truth for schema, rule placement, anti-patterns, and audit checklist) — this skill defines only the JS-specific encoding, assembler code, and gotchas.
-
aleonsa Skill Fastapi SecurityFastAPI security best practices — JWT authentication with python-jose, OAuth2, role-based access, CORS, rate limiting, security headers, and input validation.
-
aleonsa Skill Multi Tenant SaasMulti-tenant SaaS patterns — tenant isolation strategies, row-level security, tenant-aware SQLAlchemy models, RBAC, subdomain routing, and Alembic migrations for shared schema.
-
aleonsa Skill Fastapi VerificationVerification loop for FastAPI projects: Alembic migration checks, linting, async tests with coverage, security scans, and deployment readiness before release or PR.
-
openclawandroid Bundle Claw ScoreAudit or refresh OpenClaw maturity scorecard docs from root taxonomy, maturity scores, and QA evidence artifacts without using maintainer discrawl data or committed inventory reports.
-
openclawandroid Bundle Release Openclaw CIRun, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.
-
aiagentskills Bundle Docs SyncAnalyze main branch implementation and configuration to find missing, incorrect, or outdated documentation in docs/. Use when asked to audit doc coverage, sync docs with code, or propose doc updates/structure changes. Only update English docs (docs/src/content/docs/**) and never touch translated docs under docs/src/content/docs/ja, ko, or zh. Provide a report and ask for approval before editing docs.
-
ruvnet Skill Security ScanRun full security scans on the codebase using Ruflo security tools. Use when reviewing PRs for security regressions, auditing auth/input-handling code, before production deploys, or when the user asks for a security check at quick/standard/deep depth.
-
allanwessels Skill Audit Then Fanout FixWhen a class of bug keeps slipping through tests, run a coverage-matrix audit first, then fan out fix agents per gap — don't whack-a-mole individual failures.
Audited -
chili-piper Bundle User OffboardingSafely removes a departing Chili Piper rep — surfaces open meetings that need reassignment, removes them from workspaces and teams, and produces an audit trail — making rep offboarding repeatable and zero-leak
-
chili-piper Bundle Concierge Router ConfigurationCreates, reads, updates, and deletes Chili Piper Concierge routers — the web-form routing configs that decide which rep a form submission books with. Always-live writes with dry-run diffs and representability checks; the write complement to concierge-debugger/routing-audit.
-
fergius-engineering Skill Entry Point AuditUse when adding any cross-cutting change - a new gate, limit, permission check, or rule that must apply everywhere.
-
forsvn-labs Bundle Knowledge ReviewAudit the authority, freshness, and uncertainty of the sources and claims behind a decision, and reconcile conflicting evidence. Use for research synthesis, factual-claim checks, or reframing a recommendation built on weak sourcing. This is knowledge review, never code review.
-
afonsoft Bundle Quality Test ImplementationUse when improving code quality, reducing technical debt, or raising test coverage in .NET, Java, or Python repositories — fixing static-analysis warnings (Roslyn/Sonar, SpotBugs/Checkstyle, Bandit/Ruff), resolving security CVEs, and applying SOLID/DDD/Clean Architecture. Do NOT use for a single-file cosmetic edit, a focused review of one change, or as a substitute for `code-review-and-quality`; this is a whole-repo quality intervention, not a localized fix. Part of the afonsoft/skills collection.
Audited -
alexzhu0 Skill Dependency Upgrade Risk ReviewUse when reviewing dependency upgrades, package-lock diffs, SDK version changes, release notes, or migration guides for breaking changes, security impact, tests, and rollout risk.
Audited -
austintgriffith Bundle Evm Audit DosEVM smart contract audit checklist for denial-of-service and griefing attacks. Covers gas griefing, unbounded loops, returndata bombing, block stuffing, and DoS via revert. Use when auditing protocols with loops, external calls, or time-sensitive operations. Load references/checklist.md for the full checklist.
-
austintgriffith Bundle Evm Audit Erc20Weird ERC20 token edge cases that break protocols. Covers fee-on-transfer, rebasing, missing return values, blocklists, multiple addresses, flash minting, ERC777 hooks, approval race conditions, and more. Load when the contract interacts with ANY ERC20 tokens.
-
austintgriffith Bundle Evm Audit Erc721EVM smart contract audit checklist for ERC721/ERC1155 tokens. Covers weird NFT behaviors, dual-standard tokens, wrapped/legacy collections, permit issues, fractionalization, pausability, blacklists, and upgradeable NFTs. Use when auditing protocols that interact with arbitrary ERC721/ERC1155 tokens. Load references/checklist.md for the full checklist.
-
austintgriffith Bundle Evm Audit MasterMaster index for EVM smart contract security audit skills. Load this FIRST for every audit to determine which specialized skills to load. Contains routing table and audit methodology.
-
austintgriffith Bundle Evm Audit BridgesCross-chain bridge vulnerabilities for LayerZero V2, Chainlink CCIP, Wormhole, Across, and general bridge security. Covers message ordering, fee handling, relayer trust, dust/normalization, and configuration pitfalls. Load when auditing any cross-chain protocol.
-
austintgriffith Bundle Evm Audit Erc4337Account abstraction (ERC-4337) vulnerabilities including wallet factories, paymaster replay, session keys, EntryPoint bugs, ERC-1271 cross-account replay, and module security. Load when auditing smart wallets, paymasters, or AA infrastructure.
-
austintgriffith Bundle Evm Audit Erc4626ERC4626 vault standard vulnerabilities including inflation attacks, rounding direction, share price manipulation, first depositor attacks, compliance checks, and cross-chain vault issues. Load when auditing any ERC4626 vault or vault-like protocol.
-
austintgriffith Bundle Evm Audit GeneralGeneral Solidity/EVM security checklist — non-obvious footguns that apply to every smart contract. Covers external calls, force-feeding, pause mechanisms, read-only reentrancy, merkle trees, code asymmetry, multicall hazards, and general EVM quirks. Load this for EVERY audit.
-
austintgriffith Bundle Evm Audit OraclesOracle vulnerabilities including Chainlink staleness, minAnswer/maxAnswer circuit breakers, L2 sequencer uptime, TWAP manipulation, VRF front-running, spot price attacks, peg assumptions, and oracle decimal mismatches. Load when the contract uses any price oracle or external data feed.
-
austintgriffith Bundle Evm Audit ProxiesProxy and upgrade vulnerabilities including UUPS, transparent proxy, beacon proxy, storage collisions, metamorphic contracts, initializer issues, and function selector clashing. Load when auditing any upgradeable contract.
-
austintgriffith Bundle Evm Audit AssemblyInline assembly, CREATE/CREATE2, EXTCODESIZE, and low-level opcode vulnerabilities. Covers metamorphic contracts, constructor-time code absence, assembly math overflow, and div-by-zero returning 0. Load when the contract uses inline assembly or CREATE2.
-
austintgriffith Bundle Evm Audit Defi AmmAMM-specific vulnerabilities including Uniswap V3/V4 hooks, concentrated liquidity, swap routing, TWAMM, slippage, and DEX integration pitfalls. Load when auditing any AMM, DEX, swap router, or Uniswap V4 hook.
-
austintgriffith Bundle Evm Audit FlashloansEVM smart contract audit checklist for flash loan attack patterns. Covers flash loan governance attacks, oracle manipulation via flash loans, flash deposit-withdraw attacks, and flash mint inflation. Use when auditing DeFi protocols vulnerable to single-transaction economic attacks. Load references/checklist.md for the full checklist.
-
austintgriffith Bundle Evm Audit GovernanceDAO governance vulnerabilities including flash loan voting, proposal execution ordering, timelock bypass, fake proposals via CREATE2, quorum manipulation, Gnosis Safe module bypasses, and reward distribution attacks. Load when auditing any governance system.
-
austintgriffith Bundle Evm Audit SignaturesSignature vulnerabilities including cross-chain replay, ecrecover pitfalls, EIP-712 domain separator issues, permit edge cases, malleability, and meta-transaction security. Load when the contract uses any off-chain signatures.
-
austintgriffith Bundle Evm Audit Defi LendingCDP, lending market, liquidation, and borrowing vulnerabilities. Covers collateral handling, health factors, auction liquidations, bad debt, interest accrual, and lending protocol integration (AAVE, Compound). Load when auditing any lending/borrowing protocol.
-
austintgriffith Bundle Evm Audit Defi StakingLiquid staking derivatives (stETH, rETH, cbETH, sfrxETH), LRTs, restaking, staking rewards, and yield farming vulnerabilities. Load when auditing staking protocols, LSD integrations, or yield aggregators.
-
austintgriffith Bundle Evm Audit Access ControlEVM smart contract audit checklist for non-obvious access control issues. Covers centralization risks, privilege escalation, two-step ownership, role management, and admin rug vectors. Use when auditing protocols with privileged roles, admin functions, or governance. Load references/checklist.md for the full checklist.
Frequently asked questions
What are Security agent skills?
Security agent skills give AI agents disciplined security workflows: code review for vulnerabilities, secret handling, dependency audits, and hardening checklists. Every skill on SkillMD also passes its own safety review before listing, with capability flags shown on each page.
Which Security skills are most installed?
Popular Security skills on SkillMD right now include security-scan, fastapi-security, claw-score. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Security skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.