原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Agent Skills

教 AI 用某种方式工作的指令集(skill),来自 200 星以上且确有 SKILL.md 的 GitHub repo · 不是 MCP server

Skill 和 MCP 有什么不同 →

30 个与“security”相符

security-audit-skill

A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings

作者:cloudflare★ 73,1561 个 skill

Skill · 操作手册

awesome-web-security

🐶 A curated list of Web Security materials and resources.

作者:qazbnm456★ 14,0571 个 skill

Skill · 操作手册

deepsec

Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

作者:vercel-labs★ 8,4191 个 skill

Skill · 操作手册

tirith

Terminal security for developers and AI agents. Intercepts homograph URLs, pipe-to-shell, ANSI injection, obfuscated payloads, data exfiltration, and malicious AI skills/configs before they execute.

作者:sheeki03★ 2,7831 个 skill

Skill · 操作手册

ShiroAttack2

shiro反序列化漏洞综合利用(仅限授权测试使用)

作者:SummerSec★ 2,6441 个 skill

Skill · 操作手册

gpt6-Astra

gpt6 Astra-claude-grok4.7-deepseekv4.1flash-glm5.3-gemini破甲越狱 · 冷咖啡 BREAK//OPEN 工作台

作者:3641397194-wq★ 2,2421 个 skill

Skill · 操作手册

agentshield

AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️

作者:affaan-m★ 1,4101 个 skill

Skill · 操作手册

sapper-v2

The first fruit of the Nüwa tree — an autonomous AI pentest legion (634-team champion, 8h unattended, 1B tokens beat 4.5B). Not just a tool: evolvable by design. Grow your own fruit on the Nüwa Foundation (Create/Language/History).

作者:N1nEmAn★ 2,109 (whole repo)2 个 skill

Skill · 操作手册

SkillSpector

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.

作者:NVIDIA★ 26,215 (whole repo)27 个 skill

Skill · 操作手册

OpenOSINT

Open-source OSINT agent: 21 public-source tools behind natural-language chat, an MCP server and a Claude Code plugin. Passive by default, no keys to start.

作者:OpenOSINT★ 1,938 (whole repo)2 个 skill

Skill · 操作手册

nanoclaw

A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

作者:nanocoai★ 31,118 (whole repo)54 个 skill

Skill · 操作手册

reverse-skill

Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Cl…

作者:zhaoxuya520★ 44,688 (whole repo)83 个 skill

Skill · 操作手册

Agentic-Bug-Hunter

AI-powered bug bounty hunting toolkit that works with or without subscription.

作者:awarexone★ 5,910 (whole repo)15 个 skill

Skill · 操作手册

CyberStrikeAI

The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

作者:AIPentest★ 8,660 (whole repo)24 个 skill

Skill · 操作手册

bkn-foundry

BKN Foundry is the Ontology back-end foundation of OpenBKN. It transforms ontology-driven business semantics into runtime services: data, logic, actions, security governance, and observability.

作者:openbkn-ai★ 1,363 (whole repo)4 个 skill

Skill · 操作手册

ctf-skills

Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more

作者:ljagiello★ 3,717 (whole repo)11 个 skill

Skill · 操作手册

SkillEvaluator

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

作者:NVIDIA★ 1,587 (whole repo)6 个 skill

Skill · 操作手册

skills

Pashov Audit Group Skills

作者:pashov★ 1,312 (whole repo)5 个 skill

Skill · 操作手册

redamon

Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what it finds. MCP both ways: plug in any MCP server as a tool, or drive RedAmon from Claude Code or your…

作者:samugit83★ 3,406 (whole repo)18 个 skill

Skill · 操作手册

agent-scan

Security scanner for AI agents, MCP servers and agent skills.

作者:snyk★ 3,243 (whole repo)20 个 skill

Skill · 操作手册

agent

Agentic offensive-security in your terminal

作者:PentesterFlow★ 1,455 (whole repo)10 个 skill

Skill · 操作手册

Claude-Red

claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.

作者:SnailSploit★ 11,014 (whole repo)78 个 skill

Skill · 操作手册

DeepCamera

Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your home via Telegram, Discord or Slack. Pluggable AI skills. OpenAI, Google…

作者:SharpAI★ 3,143 (whole repo)24 个 skill

Skill · 操作手册

skill-scanner

Security Scanner for Agent Skills

作者:cisco-ai-defense★ 2,732 (whole repo)21 个 skill

Skill · 操作手册

匹配搜索的 MCP

Snyk MCP

Easily find and fix security issues in your applications leveraging Snyk platform capabilities.

作者:snyk广泛使用↓ 76.2万/周★ 626个月前更新

MCP · 连接服务在你的电脑上运行✓ 服务方 · snyk.io

Security Detections

Search security detections across Sigma, Splunk, Elastic, KQL, Sublime, CQL and Jamf with ATT&CK.

作者:MHaggis正在增长↓ 1661/周★ 52811天前更新

MCP · 连接服务在你的电脑上运行

HOL Guard

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

作者:hashgraph-online广泛使用↓ 7083/周★ 110711天前更新

MCP · 连接服务在你的电脑上运行

Agent Security Scanner MCP

Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.

作者:sinewaveai正在增长↓ 2693/周★ 1239个月前更新

MCP · 连接服务在你的电脑上运行

CrowdStrike Falcon MCP Server

Connects AI agents with CrowdStrike Falcon for security analysis and automation.

作者:CrowdStrike广泛使用↓ 1.9万/周★ 28212天前更新

MCP · 连接服务在你的电脑上运行

SonarQube MCP Server

Analyze code quality and security with SonarQube Server or Cloud directly in AI assistants.

作者:SonarSource正在增长★ 6885天前更新

MCP · 连接服务在你的电脑上运行

查看所有匹配“security”的 MCP →