Havuz

Fail-closed swarm orchestration with epoch-fenced work and late-completion rejection.

AVault - Call Recorder (No Root Required) | Privacy-first, hardware-encrypted audio vault for Android 12-16+. Rootless call recording via Sh

nas: a zero-dependency Python CLI + MCP server for Synology DSM 7. One-command audit and fix for the C3RB3R / .L0CK3D ransomware campaign; h

Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 archite

Fast, self-contained vulnerability scanner (single Go binary) for web apps, APKs and binaries - extensible with JSON and nuclei YAML templat

Local, evidence-based application security assessment engine and Claude Code plugin

Heuristic Solidity/DeFi security review toolkit — flags suspicious patterns to review, backed by Foundry scenarios. Educational / authorized

Skill para Claude, Codex, Cursor e outros agentes: check pré-lançamento do seu app com 20 checagens de segurança + 10 de prontidão (Lovable,

Copy 2FA codes on your Mac with one shortcut: verification codes from Mail and Messages plus a built-in TOTP/HOTP authenticator. Free, open

A Lean backend framework whose authorization safety is formally proven. The developer writes only a Cedar schema and policies; handlers are

SOC, incident response and SecOps for Linux servers in one agent: learns each host, watches it with zero-token sensors, triages with a small

A daily vulnerability briefing for AI-agent-managed machines — deterministic matching against OSV + CISA KEV; the LLM only explains. MIT

Catch .env secrets leaking into git: a pre-commit hook and CLI that fails when an API key or any value of your env files is staged, tracked

A honeypot and guestbook for AI agents that land on a machine they weren't invited to

A free, public vulnerability feed: CVE, GHSA, OSV, CISA KEV and EPSS merged into one entry per vulnerability. RSS, JSON API and MCP. Docs an

给 AI 生成代码做安全审阅的终端工具：410 条漏洞清单，20 条本地规则 + 模型逐条判定（带证据核实），看完 diff 再决定要不要写（Rust）

🔓 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

Agentshield is open source defense for Kubernetes and AWS. It learns how your workloads really talk, flags lateral movement with evidence, a

Research into flattening compaction strategics

The agentic pentesting environment that lives on your machine. AI agent teams, visual workflows and your own tools, 100% local.

LordOS — a free, fast and secure GNU/Linux distribution based on Debian, with its own desktop environment: display server and Wayland compos

Published: 2026-10-18

Published: 2026-10-18

Self-hosted pentest engagement management and report.

A code reviewer that reports only what it can prove: a test that shows the bug, or the data that confirms the risk. Open source, built by a

Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.

WireGuard, AmneziaWG, Cisco AnyConnect and Tailscale in one native, free and open-source macOS VPN client: SwiftUI app, Network Extension, k

Count Patchula vants to update your deps. A modern dependency updater with strong defaults.

MCP security scanner & config linter for AI coding agents. Finds leaked secrets, risky commands, broad permissions and invalid MCP servers i

Scan a built static site (dist/, build/, out/) or live URL and generate a tight Content-Security-Policy with sha256 hashes for inline code.

CI-friendly CLI and API that fails builds when deployed URLs are missing or misconfigure HTTP security headers (HSTS, CSP, COOP, cookies...)

HTTPS overlay for operators. macOS and Android clients. Secure admin session that holds through short disconnects and packet loss. Protocol

对Artex的二次开发

Free local guardrail for AI coding agents: every tool_call judged on-device (regex + Laya), allow/review/block

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

AI 自主渗透测试 · 红队作战平台 | 多 Agent 自主推进 · 漏洞情报运营 · 后渗透与 C2 | LLM 三通道轮询 | 全程证据留痕 | 原百度攻防赛冠军项目独立演进版

Make AI-written code production-ready, with proof. Agent skill for Claude Code, Codex, GitHub Copilot & Gemini CLI: locks behavior, finds bu

Lab-RATS is an open-source, lightweight Android Remote Administration framework packed with powerful monitoring and interaction capabilities

Rhea.js: secure, convention-driven backend framework for Node.js and Express 5. TypeScript, security defaults, auth, CLI, plugin API.

Styx is where everything converges: every repo you work in, the AI coding agents building in them, and every login they need to ship. Switch

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

Global edition of ARTEX — an LLM multi-agent autonomous penetration-testing framework. English default, switchable to Korean/Chinese/Spanish

Open source AI code review for coding agents. A separate reviewer checks every change your agent writes before you push, in Claude Code, Cod

Catch risky npm dependency changes before they merge.

Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with defau

CWE-602 客户端鉴权脆弱性白盒审计方法论与纵深防御加固研究框架

One-click sandboxes for AI agents, with egress policy, MCPs, skills and audit. Built on NVIDIA OpenShell.

Evidence-driven Java security review workbench

eBPF Prometheus exporter for AI-agent activity — per-agent tools, domains, ports, files, CPU & network — with a Grafana dashboard. A yeet se

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.