ai-security

57 projects share this GitHub topic

Lines connect members that are measurably related to each other. Dot size reflects stars.

🧬 Members

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.

Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack…

This repository is maintained by Omar Santos (@santosomar) and includes thousands of resources related to…

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt…

The Ultimate Open-Source Security Arsenal for Hackers, Enterprises, and AI…

★ 9.1k · GitHub ↗

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra…

claude-code-ultimate-guide

The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and…

🐢 Open-Source Evaluation & Testing library for LLM Agents

Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a…

★ 4.4k · GitHub ↗

secure multiplexed execution paths for agents - zero trust, zero setup, zero latency.

LeanCTX is the Context Gateway for AI Systems. Select task-relevant context, apply supported controls,…

secure-code-game

Learn to code securely while having fun through our popular open source in-editor experience, designed for…

Open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate…

pentest-ai-agents

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized…

Open-source AI-powered offensive security harness for automated penetration testing.

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed…

ARTEX · AI autonomous penetration testing system (multi-agent LLM, Go + Next.js) · AI…

★ 2.1k · GitHub ↗

ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.

Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a…

Break your AI before they do. Join Discord: https://discord.gg/NXXz8JG74

NeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various…

AttackGen is a cybersecurity incident response testing tool that leverages the power of large language models…

An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given…

A security scanner for your LLM agentic workflows

Break your AI before they do.

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages,…

CLI security scanner built for the agentic era. Detects CI/CD misconfigs, agent permission risks, MCP tool…

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket…

api-relay-audit

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution,…

Enterprise AI bastion host for secure AI API and MCP access, with unified proxying, RBAC, audit logs, rate…

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data…

emilia-protocol

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected…

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use,…

Open-source adversary emulation for AI agents and MCP servers.

PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic…

awesome-MLSecOps

A curated list of MLSecOps tools and resources for securing machine learning and AI systems - adversarial ML…

Deterministic safety solutions for probabilistic AI agents

Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement,…

Project CodeGuard is an AI model-agnostic security framework and ruleset that embeds secure-by-default…

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

SecureClaw - Security Plugin and Skill for OpenClaw OWASP-Aligned

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it…

An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG…

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply…

agent-skills-hub

Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, trending…

Container-free, deny-by-default sandbox for AI coding agents. Kernel-enforced filesystem, network, and…

Autonomous AI-powered security scanning platform — CLI scanner, web dashboard, and one-command Docker…

Agentic AI EDR for developer workstations and autonomous agent swarms. Build Swarm Detection & Response…

A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors…

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution,…

Find and govern AI attack surfaces in application code at PR time. Free, OSS, runs offline.

Ethicore Engine® is an AI safety, ethics, and compliance platform. This repo consists of the open-source…

The Anti-Virus for AI Artifacts & RAG Firewall. A static analysis tool scanning Models and Notebooks for RCE,…

Ready-to-run examples showing NoPII PII protection with OpenAI, Anthropic, LangChain, LlamaIndex, and more

AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections,…

★ 63 · GitHub ↗

Zero-code LLM security & observability proxy. Real-time prompt injection detection, PII scanning, and cost…

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII…

🔗 Related families

llm-security 38 security 114 prompt-injection 27 cybersecurity 51 agent-security 23 security-tools 38 penetration-testing 32 owasp 10

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.