Havuz

The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of

Open-Source alternative app store for Android aimed to provide a secure Google Play alternative, offering verified, open-source apps with bu

Run Windows and Linux programs on Windows, Linux and Android. A user-mode NT and Linux kernel emulator with WHP/KVM acceleration.

An open taxonomy and scoring framework for evaluating AI agent sandboxes: 7 defense layers, 7 threat categories, 3 evaluation dimensions, 27

🔓 An AI web-pentest skill for Claude Code. Point it at a site you're authorized to test — it maps the attack surface, works through the OWAS

The AI-friendly binary analysis & decompilation engine — 1:1 lift, built on LLVM [WIP]

Universal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk

Self-hosted personal AI agent with a WebUI, memory, tools, MCP, sub-agents and automations. Connect local or cloud LLMs.

Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.

The self-hosted token, certificate, license, and secret expiration manager with automated Certificate Lifecycle Management (CertOps) for tea

Docker sandbox for the Claude Code CLI. Runs Claude against one project folder — including with --dangerously-skip-permissions — while your

No WiFi? Now WiFi. One command. 27 techniques. Bypass any captive portal.

Free client-side password and key generator for secure passwords, API keys, UUIDs, JWT secrets, and encryption keys. Powered by the Web Cryp

🔒 Jail OpenCode, Claude Code, Copilot CLI and OmO in micro-VMs: only your project folders, only the networks you allow.

Free, open-source SSH client, SFTP, tunnels, database GUI and a secure AI-agent (MCP) bridge in one app a MobaXterm, PuTTY and Termius al

CLI for Local Isolated Environments for Coding Agents

Practical DevOps interview questions for Aspiring DevOps Engineers

Open-source AI vulnerability discovery

Prompt-injection, jailbreak and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanit

Claude and ChatGPT now log into your app as your customers. OneHuman decides what they can see and do. Join our community: https://discord.g

Distributed, centrally-controlled Web Application Firewall built on pingap & Cloudflare Pingora. Semantic attack detection, Cloudflare-style

Security-testing methodology as portable, tool-agnostic agent skills for Claude Code and any agent runtime: white-box bug hunting, AI-agent

Public source of the Dreadnode capabilities in app.dreadnode.io — agents, tools, skills, MCP servers, and workers.

Open-source macOS security app with local Endpoint Security monitoring, YARA scanning, behavioral detection, Email Guard, and network filter

Policy-aware AI permission reviewer for OpenCode V1 and V2. Evaluates tool and command requests, allowing, denying with feedback, or escalat

Helix is ​​a powerful self-learning AI agent with memory, skills, and the ability to recall tools. It learns from successful tasks and creat

Seven Agent Skills for NestJS implementation, architecture, OOP, code and feature audits, runtime performance, and safe Git publication.

Open-source, self-hosted security pipeline for IT, AI and OT. Logs in. Evidence out.: OCSF normalization, 46 detection rules (MITRE/ATLAS/IC

面向 CTF 竞赛评测平台（TSec Benchmark）的自动化 Web/逻辑漏洞挖掘与利用 Agent：分层调度 + 多会话并发 + 跨会话共享黑板 + 平台权威校验

Run Claude Code, Codex and other coding agents in a local VM on a clone of your project, then review their changes like a pull request. Mac

OpenLock — a free, open-source App Lock for Android. Lock any app behind a PIN, pattern, or fingerprint, with Device-Admin uninstall protect

PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders befo

Practical Linux server hardening — every item is failure → fix → verify. SSH, firewall, service binding, secrets, DB auth, and more.

🔍 Detect API model dilution and fingerprint which LLM is actually running behind any OpenAI-compatible or Anthropic endpoint

Stop sending crypto to the wrong address. Kenning checks every wallet address you copy and catches address poisoning and clipboard-hijacking

json-guard, JSON metnini JSON.parse öncesinde tarayarak boyut, iç içe geçme, anahtar ve string uzunluğu sınırları uygulayan bir TypeScript kütüphanesidir.

Neden yükseliyor · JSON kaynaklı hizmet engelleme riskini somut bir demo ve ölçümle anlatması dikkat çekmiş olabilir. Ancak 3 günlük yaş, 77 yıldız, 2 commit ve 1 farklı yazar verisi erken ilgiyi gösterir; benimsenme veya olgunluk kanıtı değildir.

GitHub Actions workflow’larında kullanılan JavaScript action’ların kaynak kodundan `dist/` çıktısını yeniden oluşturup commit edilmiş dosyalarla karşılaştırır.

Neden yükseliyor · Repo yalnızca 1 günlük ve 30 yıldızlı; son 28 günlük commit ve farklı yazar verisi ölçülmediği için yükseliş eğilimi doğrulanamıyor. README’nin işaret ettiği supply-chain riski ve belirli bir denetim boşluğunu hedeflemesi ilgi çekmiş olabilir, ancak bu ilginin nedeni veya kullanıcı benimsemesi mevcut verilerle kanıtlanmış değil.

Blitz Strike, penetration-testing iş akışını MCP üzerinden sunan ve bulguları canlı doğrulamaya yönelen bir güvenlik aracıdır.

Neden yükseliyor · 15 günlük yaşına rağmen 512 yıldız almış; MCP tabanlı agent iş akışlarıyla penetration testing'i tek entegrasyonda toplama vaadi dikkat çekiyor. Ancak son 28 günde yalnızca 2 commit ve 1 farklı yazar görünmesi, bu ilginin aktif geliştirme veya topluluk katkısıyla henüz desteklenmediğini gösteriyor.

ThreatIntel-Aggregator, güvenlik feed’lerini birleştirip tehditleri analiz eden ve varlıklarla ilişkilendiren self-hosted bir threat intelligence platformudur.

Neden yükseliyor · 14 günde 54 yıldız almış; bu, yeni bir repo için dikkat çekici bir başlangıç. Ancak yalnızca 3 commit ve 2 farklı yazar bilgisi var; yükselişin nedenini veya kullanıcı benimsemesini gösteren bağımsız kanıt mevcut değil.

ToolReplay, AI agent’ların tool-call transcript’lerini determinism, yinelenen çağrılar ve izin kapsamı açısından denetleyen bir Python CLI’dir.

Neden yükseliyor · AI agent’ların davranışını denetlenebilir ve tekrarlanabilir kılma ihtiyacına doğrudan hitap ediyor; README’de örnek girdi ve çıktıyla çalışan bir kullanım gösteriliyor. 13 günde 184 yıldız dikkat çekiyor, ancak son 28 günde 2 commit ve 1 farklı yazar bakım ve benimsenmenin sürdürülebilirliği için henüz zayıf kanıt.

droast - a dockerfile linter that actually has opinions 🔥

DianXing - AI-Driven End-to-End Code Security Auditing

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential con

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open

Mantis Hack

发现藏在前端代码里的 API，验证未授权访问风险 · 动态浏览器追踪 × JavaScript 静态分析

Open source agentic SAST. The engine behind hundreds of disclosed zero-days. 100+ AI security agents, any repo or PR diff, bring your own mo

A CI/CD Red Team Framework for demonstrating Build Pipeline security risks.

AI red-team platform. Autonomous LLM agents run a penetration test end to end inside a Kali container and write the report. LangGraph plan/a

Let AI agents investigate and operate infrastructure through declared actions, bounded by policy and host-side checks. Approvals when requir