#ai-security Repositories
90 repositories total
Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
This project aims to provide a central repository for many useful Tsunami Security Scanner plugins.
AI-first security scanner. NEW in v2026.7: Claude Code compromise detection โ vet .claude/ hooks, permissions & skills before you clone โ plus an always-on AI attack-signature scanner and native Rust & PHP rules. Also: medusa scan --git to vet any repo, medusa secrets scan for leaked API keys. 40,000+ patterns, zero setup.
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
A deliberately vulnerable banking application designed for practicing Security Testing of Web App, APIs, AI integrated App and secure code reviews. Features common vulnerabilities found in real-world applications, making it an ideal platform for security professionals, developers, and enthusiasts to learn pentesting and secure coding practices.
Reconmap is a collaboration-first security operations platform for infosec teams and MSSPs, enabling endโtoโend engagement management, from reconnaissance through execution and reporting. With built-in command automation, output parsing, and AIโassisted summaries, it delivers faster, more structured, and highโquality security assessments.
An Axum-based Rust web framework with Lean 4-verifiable application kernels that run on servers, bare-metal embedded devices, and GPUs, plus integrated security testing.
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks. Website: https://apirelayaudit.com
Tencent Cloud Intelligent Penetration Hackathon Official repository of Tencent Cloud Intelligent Penetration Hackathon. Showcasing top open-source projects of LLM-based autonomous penetration agents, including multi-agent collaboration, automated penetration, AI-driven offensive security, and intelligent attack-defense solutions.
The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic core, no API key needed, JSON and SARIF output.
Worldwide Premiere!!! The Most Comprehensive Cybersecurity Interview Questions with Reference Answers (Covering Network Protection, Red Teams, Reverse Engineering, Cryptography, Binary, AI, Blockchain)
Krawl is a customizable, lightweight, cloud-native web deception server and anti-crawler that creates fake web applications with low-hanging vulnerabilities using realistic, randomly generated decoy data and AI-generated HTML templates.
A comprehensive security checklist for MCP-based AI tools. Built by SlowMist to safeguard LLM plugin ecosystems.
Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.
This tool is designed to help penetration testers and network administrators identify potential security threats, especially those targeting web applications such as SQL injection, XSS, and WebShells. Its modular desig The tool is suitable for HW Red Teams to conduct in-depth analysis of network traffic, assisting professionals such as security researchers, penetration testers, and network administrators in identifying potential security threats, especially attacks targeting web applications (such as SQL injection, XSS, WebShells, etc.). Its modular design allows users to freely select and customize various functional modules based on actual needs.
A source-grounded course and architectural reference for engineers designing systems that must survive real traffic, partial failure, security review, and changing requirements, spanning enterprise system design, distributed systems, AI systems, cybersecurity, reliability, cloud, HPC, edge, and mission-critical infrastructure.
Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
AI Code Security Anti-Patterns distilled from 150+ sources to help LLMs generate safer code.
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.
MCP for Security: A collection of Model Context Protocol servers for popular security tools like SQLMap, FFUF, NMAP, Masscan and more. Integrate security testing and penetration testing into AI workflows.
Open-source adversary emulation for AI agents and MCP servers.
Self-hosted runtime control plane for AI agents. Observe, approve with HITL, or block rogue tool calls before they executeโpreventing secret leaks, prompt injection, supply-chain attacks, and moreโfrom a local dashboard. Agent-agnostic (Claude, Codex, LangChain, etc.).
A roadmap describing the required skills, learning resources and sample tools to become an AI Engineer
Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.
๐ก๏ธ Security audit CLI for Model Context Protocol (MCP) servers โ scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.
Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.
vArmor is a cloud-native container hardening system that leverages AppArmor/BPF/Seccomp and NetworkProxy technologies to enforce access control from system calls to application protocols โ protecting workloads including AI Agents.
AI-powered subdomain enumeration tool with local LLM analysis via Ollama - 100% private, zero API costs
AI-powered Docker security scanner that explains vulnerabilities in plain English. An OWASP Lab Project.
AgentSkillsHub (agentskillshub.top) โ a security-graded directory of open-source Claude skills, MCP servers, and AI agent tools, updated every 8 hours
This document curates open-source projects, academic papers, capability benchmarks, and commercial solutions (international and China) in AI penetration testing, LLM red teaming, autonomous offensive agents, and vulnerability discoveryโaimed at helping researchers, security engineers, and enterprise decision-makers quickly form a holistic view.