Trending repositories: security

50 of 50 repositories

• affaan-m/ECC

  The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

  AI summary: A C-based educational implementation of Elliptic Curve Cryptography illustrating core cryptographic principles.

  272,795securityJavaScriptMITai-agentsanthropicclaudeclaude-code

• trimstray/the-book-of-secret-knowledge

  A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.

  AI summary: A massive, curated collection of manuals, cheatsheets, and CLI tools for IT professionals and researchers.

  247,846developer-toolsMITawesomeawesome-listbsdcheatsheets

• x1xhlol/system-prompts-and-models-of-ai-tools

  FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

  AI summary: A collection of leaked or reverse-engineered system prompts and model details from popular AI tools.

  144,018ai-mlGPL-3.0aiboltcluelycopilot

• Developer-Y/cs-video-courses

  List of Computer Science courses with video lectures.

  AI summary: A community-curated directory of university-level computer science video lectures organized by academic discipline.

  83,609learningalgorithmsbioinformaticscomputational-biologycomputational-physics

• caddyserver/caddy

  Fast and extensible multi-platform HTTP/1-2-3 web server with automatic HTTPS

  AI summary: Fast, multi-platform HTTP/1-2-3 web server with automatic HTTPS.

  76,454infrastructureGoApache-2.0acmeautomatic-httpscaddycaddyfile

• asgeirtj/system_prompts_leaks

  Documented system prompts from Anthropic - Claude Fable 5.1, Opus 5.5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-6-Astra, Codex. Google - Gemini 3.8 Flash, 3.1 Pro, Antigravity. xAI - Grok, Grok Bot, Cursor, Kimi and more! Updated regularly.

  AI summary: An analytical archive of leaked system prompts from major commercial AI applications.

  68,725securityJavaScriptCC0-1.0aiai-agentsai-promptsanthropic

• usestrix/strix

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

  AI summary: An open-source AI penetration testing tool utilizing autonomous agents to find and exploit app vulnerabilities.

  66,273securityPythonApache-2.0agentsai-hackingai-penetration-testingai-pentesting

• KeygraphHQ/shannon

  Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

  AI summary: A high-performance, open-source knowledge graph engine optimized for fast querying and AI integration.

  48,554dataTypeScriptAGPL-3.0ai-penetration-testingai-securityapi-securityappsec

• mukul975/Anthropic-Cybersecurity-Skills

  817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

  AI summary: A vast library of structured cybersecurity skills for AI agents, mapped to multiple industry frameworks.

  33,715securityPythonApache-2.0ai-agentsclaude-codecloud-securitycybersecurity

• imthenachoman/How-To-Secure-A-Linux-Server

  An evolving how-to guide for securing a Linux server.

  AI summary: A comprehensive, step-by-step guide and reference for hardening and securing internet-facing Linux servers.

  31,747securityCC-BY-SA-4.0cc-by-sahardeninghardening-stepslinux

• nanocoai/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

  AI summary: A lightweight AI assistant framework that securely runs agents in isolated Linux containers.

  30,862productivityTypeScriptMITai-agentsai-assistantclaude-codeclaude-skills

• cilium/cilium

  eBPF-based Networking, Security, and Observability

  AI summary: An eBPF-based networking, security, and observability solution for cloud-native environments and Kubernetes clusters.

  25,601infrastructureGoApache-2.0bpfcncfcnicontainers

• simplex-chat/simplex-chat

  SimpleX - the first messaging network operating without user identifiers of any kind - 100% private by design! iOS, Android and desktop apps 📱!

  AI summary: A hyper-secure messaging platform operating without user identifiers of any kind to guarantee absolute privacy.

  19,517securityHaskellAGPL-3.0chatdouble-ratchete2eeencryption

• NVIDIA/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.

  AI summary: A specialized security scanner that detects vulnerabilities and malicious patterns in AI agent skills.

  19,325securityPythonApache-2.0agent-securityagent-skillsagentic-aiai-security

• ifixai-ai/iFixAi

  Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

  AI summary: A specialized CLI tool for evaluating the security vulnerabilities of AI agents.

  18,942securityPythonApache-2.0agent-evaluationaiai-alignmentai-evaluation

• google/magika

  Fast and accurate AI powered file content types detection

  AI summary: A highly optimized, AI-powered file type detection tool achieving 99% accuracy within milliseconds.

  18,690ai-mlRustApache-2.0aideep-learningfiletypekeras-classification-models

• RightNow-AI/openfang

  Open-source Agent Operating System

  AI summary: A highly secure, zero-dependency Rust framework for deploying autonomous AI agents with specialized capabilities.

  18,211ai-mlRustApache-2.0agent-frameworkai-agentsllmmcp

• opensandbox-group/OpenSandbox

  Secure, Fast, and Extensible Sandbox runtime for AI agents.

  AI summary: A secure, fast, and extensible serverless sandbox runtime designed for executing AI agent code.

  15,649infrastructurePythonApache-2.0aiai-agentai-infrakubernetes

• amnezia-vpn/amnezia-client

  Amnezia VPN Client (Desktop+Mobile)

  AI summary: A multi-platform VPN client designed to seamlessly deploy and connect to self-hosted, obfuscated private networks.

  15,320securityC++GPL-3.0cloakgfwikev2openvpn

• mvt-project/mvt

  MVT (Mobile Verification Toolkit) helps with conducting forensics of mobile devices in order to find signs of a potential compromise.

  AI summary: A forensic tool for automating the gathering of traces to identify potential compromises of mobile devices.

  15,165securityPythonOtherandroidforensicsforensics-toolsios

• TencentCloud/CubeSandbox

  Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

  AI summary: A secure, lightweight sandbox environment for safely executing untrusted code in cloud environments.

  12,798securityGoOtheragentscontainersandboxsecurity

• nearai/ironclaw

  IronClaw is an Agent OS focused on privacy, security and extensibility

  AI summary: A secure, privacy-focused Agent Operating System designed as an extensible personal AI assistant.

  12,634securityRustApache-2.0codeactopenclawrlmrust

• majd/ipatool

  Command-line tool that allows you to search for iOS, iPadOS, tvOS, visionOS, and macOS apps on the App Store, and download .ipa or macOS .pkg app packages.

  AI summary: A command-line utility for searching and downloading app packages directly from the Apple App Store.

  11,461developer-toolsGoMITappleappstoreclicommand-line

• NoeFabris/opencode-antigravity-auth

  Enable Opencode to authenticate against Antigravity (Google's IDE) via OAuth so you can use Antigravity rate limits and access models like gemini-3-pro and claude-opus-4-5-thinking with your Google credentials.

  AI summary: A secure authentication module built for OpenCode that utilizes Antigravity technology to manage sessions and zero-knowledge proofs.

  10,961securityTypeScriptMITclaudegeminigoogleopencode

• cloudflare/cloudflare-os

  Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.

  AI summary: An open-source AI productivity environment providing secure, sandboxed agent chat and application development for enterprises.

  10,757productivityTypeScriptApache-2.0ai-agentsenterprisesecurityproductivity

• astrid-runtime/astrid

  Astrid is a portable, capability-secure operating system for composable software.

  AI summary: A highly isolated, WebAssembly-based agent runtime designed for multi-tenant, zero-trust AI workloads.

  10,281systemsRustApache-2.0agent-runtimeai-agentscapability-securityllm

• superradcompany/microsandbox

  🧱 easy, fast, programmable and local-first microVM runtime and library

  AI summary: An extremely fast, locally embeddable microVM engine for safely executing highly untrusted workloads.

  8,530infrastructureRustApache-2.0agentsdockergolanglinux

• openbao/openbao

  OpenBao is a software solution to manage, store, and distribute sensitive data including secrets, certificates, and keys.

  AI summary: An open-source identity-based secrets and encryption management system, forked from HashiCorp Vault.

  8,286securityGoMPL-2.0gosecret-managementsecuritysecrets-management

• vercel-labs/deepsec

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

  AI summary: An agent-powered vulnerability scanner designed for deep, on-demand review of large-scale codebases.

  8,085securityTypeScriptApache-2.0securityvulnerability-scannerai-agentscode-review

• anthropics/defending-code-reference-harness

  Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

  AI summary: A reference implementation for evaluating and defending against vulnerabilities in AI-generated code.

  7,546securityPythonOthersecurityai-safetycode-generationsecurity-evaluation

• tech-leads-club/agent-skills

  The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence.

  AI summary: Secure, validated skill registry providing tested, production-ready capabilities for professional AI coding agents.

  7,024developer-toolsTypeScriptOtheragentaiantigravityclaude-code

• opa334/Dopamine

  Dopamine is a semi-untethered jailbreak for iOS 15 to 26(.0.1)

  AI summary: A rootless, semi-untethered jailbreak solution for modern iOS and iPadOS devices.

  6,799securityCMITiosjailbreaksecurityrootless

• Tencent/AI-Infra-Guard

  A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

  AI summary: A comprehensive security framework for auditing and protecting AI infrastructure and large language models.

  6,739securityPythonApache-2.0agentagent-securityagentic-aiai-infra

• InterceptSuite/ProxyBridge

  Proxifier Alternative to redirect any Windows/MacOS/Linux TCP and UDP traffic to HTTP/Socks5 proxy

  AI summary: A network tool that seamlessly bridges non-proxy-aware applications into interception proxies like Burp Suite or ZAP.

  6,573securityCMITccybersecurityhttp3httpproxy

• microsoft/agent-governance-toolkit

  AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

  AI summary: A comprehensive governance framework for safely deploying autonomous AI agents to production.

  6,377securityPythonMITagent-frameworkai-agentsai-safetycompliance

• bikini/exploitarium

  A single archive of public exploit PoCs and vulnerability research writeups. At the time I post these, none have been reported. Feel free to report them yourself and take credit for the CVE if handed out lulz. Please do not abuse these. I do this so to allure people into the field, and I've always found this is the most efficient way.

  AI summary: A curated, consolidated archive of reproducible exploits, vulnerabilities, and security research proof-of-concepts.

  5,149securityPythonsecurityexploitsvulnerabilitypenetration-testing

• mitchellh/vouch

  A community trust management system based on explicit vouches to participate.

  AI summary: A minimal, generic community trust management system based on explicit vouches.

  5,117developer-toolsNushellMITtrust-managementopen-source-moderationgithub-actionscommunity-governance

• V4bel/dirtyfrag

  AI summary: A highly reliable, universal Linux Local Privilege Escalation exploit chaining two kernel page-cache vulnerabilities.

  5,024securityClinuxexploitlpekernel

• cursor/cookbook

  AI summary: A collection of small, guided examples for building custom workflows, hooks, and cloud agents with Cursor.

  4,113developer-toolsTypeScriptcursor-editorai-agentsdeveloper-toolsworkflows

• sanyuan0704/sanyuan-skills

  Expert code review skill: SOLID, security, performance, error handling, boundary conditions

  AI summary: A production-grade code review skill for Claude Code focusing heavily on SOLID principles and security.

  3,931developer-toolsPythonMITcode-reviewclaude-codeagent-skillsolid