Security skills

alejandrojlamas/apk-docforge

Skill Claude CodeCodex

Use this skill when the user asks to document or audit an authorized Android APK with apk-docforge.

astroicers/security-weekly-mcp

Skill Claude CodeCodex

A workflow for maintaining a Taiwan-focused security glossary and producing weekly security reports. It supports Chinese-language term management, terminology checks, news collection, and report generation.

gabchess/safeskill

Skill Claude CodeCodex

One-click security audit for your MCP setup. Get a safety score, plain-English explanations, and fix recommendations.

mustafadeel/auth0-forms-mcp

Skill Claude CodeCodex

Fork, customize, deploy, or troubleshoot the Auth0 Who Am I MCP template as an Auth0 Custom Extension. Use when adapting this repository's MCP tools, publishing its generated Webtask artifacts, provisioning its Auth0 API resource server, promoting a domain-level connection, registering an MCP client, or connecting an…

VoidNxSEC/securellm-mcp

Skill Claude CodeCodex

Advanced NixOS and Linux expertise for flake development, system debugging, packaging, security hardening, and innovative problem-solving. Triggers when working with NixOS configurations, Nix flakes, Linux system administration, debugging complex issues, building packages, compiler optimizations, security…

plenoai/metsuke

Skill Claude CodeCodex

Instructions for checking software-development compliance across pull requests, releases, and repositories. Compliance means testing whether work follows a chosen set of rules, such as SOC 2 or SLSA.

Eilodon/DPS-Superskills-MCP

Skill Claude CodeCodex

Use when completing tasks, implementing major features, or before merging — routes code review to the appropriate specialist lens (STRIDE, OWASP, ATAM, TEMPORAL, CPT, MIGRATION, PRIVACY/SECRETS) based on detected signals, with Independent Judge for Tier 3.

Hayatelin/tracehunt

Skill Claude CodeCodex

Find every account a username owns across 480+ platforms (OSINT username reconnaissance). Use when the user wants to investigate a handle, check someone's online footprint, verify an account, or do reconnaissance for AUTHORIZED security research. Returns the platforms where the handle exists plus a 0-100…

coff33ninja/ai-skills-mcp

Skill Claude CodeCodex

Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not…

ggampp/agent-reach-tech

Skill Claude CodeCodex

Tech/security research CLI for coding agents. Auto-invoke when the user asks to research, evaluate, compare, or monitor open source projects, libraries, CVEs, vulnerabilities, security advisories, GitHub repos, tech trends, Hacker News, or needs structured web research beyond a single URL fetch. Triggers: pesquisar…

ByJH/airlock

Skill Claude CodeCodex

Gate an agent extension before you install it. Audits a skill, MCP server, or tool repo and returns allow, quarantine, or block with line-level evidence.

alex-jb/shadow-perception-mcp

Skill Claude CodeCodex

Pre-submit council for trading tickets. Five voices review a JSON trade ticket for Kelly-cap compliance, missing stop-loss, sector or single-name concentration limits, fat-finger qty (10× typical = BLOCK, Knight Capital 2012 lesson), and Reg BI Care Obligation on retirement accounts. Returns SHIP / REWORK / BLOCK…

Space-C0wboy/OpenCTI-MCP-Server

Skill Claude CodeCodex

Use when working with the OpenCTI threat-intelligence platform via the opencti MCP tools — explains OpenCTI's STIX data model, entity types, indicators vs observables, relationships, containers, TLP markings, confidence, connectors/ingestion, and RBAC, and maps each concept to the right MCP tool. Load before creating…

sunick2009/mcp-owasp-pentesting-guide

Skill Claude CodeCodex

Query versioned OWASP testing guides through the Pentest Guide MCP for research, comparison, applicability analysis, and candidate test planning.

yuanjianking/kasra-mcp

Skill Claude CodeCodex

🔒 Perform deep security review of the current code repository using the Kasra security engine (direct SDK or MCP).

Abdul4code/CodePecker

Skill Claude CodeCodex

Review a code change for security, standards, production-readiness, and sustainability issues against a governed rule corpus, citing the rule ID and verbatim evidence for each finding. Use when reviewing, hardening, or pre-flighting code before it merges — especially AI-generated code.

manteclaw/mcp-server-bridge-security

Skill Claude CodeCodex

Cross-chain bridge security auditing toolkit exposed as an MCP server via stdio.

manteclaw/mcp-server-ai-redteam

Skill Claude CodeCodex

AI red teaming toolkit exposed as an MCP server via stdio.

manteclaw/mcp-server-onchain-forensics

Skill Claude CodeCodex

On-chain forensics toolkit exposed as an MCP server via stdio.

manteclaw/mcp-server-bug-bounty

Skill Claude CodeCodex

Automated bug bounty hunting toolkit exposed as an MCP server via stdio.

kilroyblockchain/free2pa-devtool

Skill Codex

Add Free2PA provenance and local trust checks to an agentic application. Use when a developer asks to protect an agent, OpenClaw project, ChatGPT app, MCP server, Agents SDK workflow, skills, prompts, SOUL.md, AGENTS.md, policies, or other control files from unnoticed changes or outside-group publishers.

Gonzih/agent-keys

Skill Claude CodeCodex

Provides AI agents with autonomous API key acquisition and management via MCP.

teodorofodocrispin-cmyk/sentinel-public

Skill Claude CodeCodex

Pre-execution transaction safety check for autonomous AI agents — one capability of the SENTINEL trust oracle (sentinel-agent.dev). Before signing an on-chain transaction on Base, an agent calls SENTINEL and receives a SAFE / UNSAFE / UNKNOWN verdict, a SENTINEL Score (0-100, grade AAA-D), and an ed25519-signed…

iamsecure1920/Cordon-AI

Skill Claude CodeCodex

Detect and verify subdomain takeovers with Cordon's three-step flow, then produce a responsible PoC. Use when checking for dangling DNS, takeover candidates, unclaimed cloud resources, or NS/MX delegation issues.