Security & Testing ListingsSecurity & Testing

Atlas

Open-source local AI Agent desktop app for authorized security assessment — Electron + Mastra-powered runtime, visual pentest workflow, Kali sandbox, multi-provider LLM routing. 本地 AI 安全评估智能体桌面应用

MCPSecBench

MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols

R20 Glebis Claude Skills Security

🔒 Security & Compliance skill suite derived from glebis/claude-skills.

Claude Code Tauri Skills

Comprehensive Claude Code skills for Tauri v2 development - 39 skills covering setup, security, development, distribution, and more

AgentLeak

AgentLeak (IEEE Access 2026): benchmark for internal-channel privacy leakage in multi-agent LLM systems. Inter-agent messages leak 68.8% vs 27.2% in final outputs; output-only audits miss 41.7%. 1,000 scenarios, 7 channels, 5 LLMs. Tool & MCP server: github.com/yagobski/agentleak

PentestPi

Autonomous Penetration Testing Agent Framework with External State Memory & Anti-False-Falsification Guardrails.

Grantex

grantex is the identity, authorization, and audit infrastructure for AI agents — the "OAuth moment" for the agentic internet. We provide a universal SDK and cloud service that lets any AI agent act on behalf of a human with scoped, revocable permissions, cryptographic identity, and an immutable audit trail. Developers integrate in minutes.

MCP Cve Project

The Project shares all information on MCP related CVE's published

Toolhive Registry Server

Discover, govern and control access to MCP servers and agent skills across your organization

CyberPenda

Local-first pentest agent: Go daemon + React dashboard + Codex/Claude Code/Pi runtimes, scoped projects, Blackboard, sandbox runners

Claude Code Skills

Скиллы для Claude Code: дисциплинированный пайплайн разработки и два пред-запусковых аудита — сайта и безопасности приложения

Openqa

Agentic Testing Harness

Claude Security Skills

Claude Code security skills: /security-review, /full-scan, /security-scan — with test harness and fixtures

Claude Skills

Claude Skills for every role: 164 Claude Code skills (Agent Skills) for PM, QA, engineering, design, DevOps, sales, marketing and more. Install as a plugin.

Hoot

MCP Testing Tool — Like Postman, but for the Model Context Protocol.

Claude Skills

Battle-tested Claude Code skills for hardening vibe-coded projects. Audit, clean, and ship AI-generated codebases with confidence.

Agent Discover Scanner

The industry-standard Agentic Identity & Inventory Scanner. Automatically inventory autonomous agents (LangChain, AutoGen, CrewAI, PydanticAI) using static analysis, network heuristics, and eBPF. Foundational tool for AIBOM compliance and AgentOps governance.

Claude Security Skills

25 production-tested defensive security skills for Claude Code - WordPress, VPS, Cloudflare, Next.js hardening, AI agent guardrails, MCP security, prompt injection defense, OWASP LLM Top 10, LLM coding failure modes (slopsquatting, hallucinated APIs, sycophancy), incident response, GDPR/DACH compliance. MIT, battle-tested.

Agentshield

🛡️ The security firewall for AI agent tools & MCP servers (Claude 5, GPT-5.6, Gemini 3.8, Antigravity, Cursor, Codex, Hermes). Catch command injection, secret theft & toxic flows in <50ms. 100% offline Rust SAST + 1-click auto-fix + SARIF.

Agenttrust

Enterprise Zero-Trust AI Security & Governance Gateway: Real-Time Prompt Injection Defense, Action Scoping, HITL Approvals, Post-Quantum Merkle Audit & EU AI Act Compliance for Autonomous Agent Swarms.

Claude Skills

A Claude Code plugin marketplace for open-source maintainers — README heroes, README audits, and .NET test-coverage backfills.

Prompt Shield

Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.

Mcpflo

A visual testing tool for MCP (Model Context Protocol) servers — connect, browse capabilities, and inspect tools, resources, and prompts. Think Bruno, but for MCP.

MCP Box

Highly isolated Linux container environments optimized specifically for mcp-servers. Secure AI agent tool execution.