MCP servers and skills: search, filter by where they run, and compare.
Zero-key cybersecurity MCP server: grade any site security A+ to F, check if a CVE is actively exploited, get plain-English MITRE ATT&CK defenses. No API keys, no signups.
PythonMITFew starsNo key
MCP server that audits a Supabase project: anon-key probe, RLS policy audit, cross-tenant test.
Node.jsMITFew starsNo key
Hướng dẫn kỹ thuật an ninh cho AI Agent · Agent Security Technical Guidelines (public draft 0.1.0)
SkillCC-BY-4.0★ 4Few starsNo key
Security scanning and guardrails for MCP servers and AI agents
Node.jsMITFew starsNo key
🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + C
PythonMIT★ 377No key
AegisGate MCP — Standalone Model Context Protocol security server with 23 security layers, vendored ONNX runtime, neural threat detection (L3). SSE streaming. Session management. Zero module dependenc
DockerApache-2.0Few starsNo key
An AI security and EU compliance analyst for Claude Code: OWASP LLM and Agentic Top 10 reviews, plus GDPR, ePrivacy, EU AI Act, NIS2, CRA, DORA and Data Act compliance.
SkillMIT★ 1Few starsNo key
everthread on npm: a plain-English website security check for the terminal, plus an MCP server for agents
Node.jsMITFew starsNo key
Pre-ship quality gate skill for coding agents, with an evidence contract for security findings — installs alongside Cloudflare's security-audit skill
SkillMITFew starsNo key
MCP servers for everyday development and security checks: OSV vulnerability lookup, security header grading, JWT decoding and verification, regex testing with ReDoS detection, cron explanation, JSON S
DockerMIT★ 1Few starsNo key
SkillMITFew starsNo key
An automated way to discover practical, hands on penetration testing projects using Claude, with structured learning roadmaps, relevant security tools, and progressive challenges to build real world c
SkillMIT★ 19No key
Security help for defenders: grade your site's security headers (fixes + README badge) and read logs/code to find what happened. Claude Code plugin, MCP server, no install.
SkillMIT★ 1Few starsNo key
Adversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression testing and reports.
PythonApache-2.0★ 17No key
Evidence-first Android and iOS security audits with CLI, TUI, MCP, public vulnerability intelligence, and OWASP-aligned evidence.
PythonMITFew starsNo key
Cybersecurity for AI founders and vibe coders. A pre-push security gate for apps built with Claude Code, Cursor, Lovable and Bolt.
Node.jsMITFew starsNo key
🛡️ npm audit for the AI agent ecosystem. Static security scanner for MCP servers, Agent Skills, AGENTS.md and tool code — detects prompt injection, hidden instructions, data exfiltration and supply-c
Node.jsMITFew starsNo key
🦀⚡ Community skill pack & CLI for Genspark Claw, OpenClaw & Hermes agents — 5 production-ready SKILL.md skills (deep research, reports, slides, browser automation, AI call prep), zero-dependency Node
Node.jsMIT★ 368No key
Security scanner for MCP servers, source trees, and packages, with explicit findings and coverage reporting.
GoApache-2.0★ 20No key
A skill pack that turns your AI into an expert website builder: current research, design, code, accessibility, speed, SEO and security, alone or as a team.
SkillMIT★ 3Few starsNo key
对任意网站进行 AI-Agent 就绪度、SEO 可发现性与安全审计与加固/Conduct AI-Agent readiness, SEO discoverability, and security audit and reinforcement for any website
SkillApache-2.0★ 1Few starsNo key
Local-first, deterministic security scanner for Model Context Protocol (MCP) servers. Cross-tool toxic-flow analysis, Unicode-smuggling decode, prompt-injection & supply-chain detection, with an audit
Node.jsMIT★ 1Few starsNo key
OfficialNode.jsMITNo key
Who stands behind it
