pentagi

PentAGI P enetration testing A rtificial G eneral I ntelligence コミュニティに参加しましょう！ セキュリティ研究者、AI愛好家、そして倫理的なハッカーの仲間たちとつながりましょう。サポートを得たり、知見を共有したり、PentAGIの最新開発情報を入手したりできます。 ⠀ 目次 概要 機能 アーキテクチャ 高度なエージェント監視 クイックスタート ログイン後のPentAGIの使い方 APIアクセス LLMプロバイダ設定 Ollama OpenAI Anthropic Google AI Gemini...

agentbox

Agentbox - コーディングエージェントサンドボックス エージェントをサンドボックス化する完璧な方法は（まだ）ありませんが、コンテナは実用的な出発点です。 AgentboxはDockerベースのコーディングエージェントサンドボックスで、元々はBatrachian Toadに触発され、現在はより多くのツールに一般化されています。 複数のエージェントセッションを実行するためにwebtermと連携して動作する隔離環境を提供します。 機能 デフォルトコンテナは以下を提供します： 開発環境 : 一般的な開発ツールを備えたDebian Trixie プリインストールされたコーディングエージェン...

livewire-honeypot

Livewire 蜜罐 一个高交互蜜罐，伪装成存在漏洞的 Laravel/Livewire 应用程序。它能捕获针对已知 Livewire CVE 的漏洞利用尝试，存储上传的恶意文件（WebShell）和远程代码执行（RCE）负载，并通过 SHA-256 去重，还能选择性地在沙箱化的 Docker 容器中执行这些负载，以提取攻击指标（IOC）——即恶意软件试图联系的 URL、IP 和域名。 出于安全考虑，系统作为两个独立的进程运行：一个Web 服务器 （负责捕获负载，无 Docker 访问权限）和一个沙箱工作者 （负责在隔离容器中分析负载）。 工作原理 root@kitploit: 攻击者...

readme2demo

readme2demo — READMEから検証済みチュートリアル＆デモ動画 ▶ readme2demoが自身のチュートリアルを生成: AIエージェントがこのリポジトリのREADMEをサンドボックス内で実行し、新しいコンテナがすべての手順をリプレイし、デモがレンダリングされます。完全な自己実行出力はexamples/readme2demoにあります。別のプロジェクトでの実行例はexamples/toolhive。 AI検証済みチュートリアル＆デモ動画ジェネレーター。...

cve-bench

CVE-Bench Un benchmark para evaluar agentes de LLM en la corrección de vulnerabilidades de seguridad reales. Los agentes se ejecutan dentro de contenedores Docker aislados y se puntúan según la suite de pruebas de seguridad del mantenedor. Requisitos Python 3.12+ Docker OPENAIAPIKEY,...

kurukshetra

Kurukshetra Kurukshetra 是一个 Web 框架，旨在成为第一个开源框架，为托管相当复杂的安全编码 挑战提供坚实基础，同时仍能在安全的沙盒环境中根据用户输入高效且动态地执行每个挑战。 Kurukshetra 由两个组件组成：用 PHP 编写的后端框架，负责管理和利用底层 Docker 系统为挑战执行提供安全的沙盒 ；以及前端，这是一个面向用户的 Web 应用程序，提供所有必要的控制功能，供管理员托管和修改挑战，供用户执行并查看每个输入的結果。 详细工具文档： https://0daylabs.com/kurukshetra/ 安装 支持的平台 Kurukshetra ...

poodle-attack-sandbox

poodle-attack-sandbox Overview This code is the test code for POODLECVE-2014-3566. POODLE stands for "Padding Oracle On Downgraded Legacy Encryption" and is a vulnerability in SSLv3.0. Warning If you use this code to carry out an attack, you may be arrested by the judicial authorities of your...

CVE-2026-72713

XAgent contains a path traversal vulnerability in the workspace file endpoint that allows self-registered or default-credential users to read arbitrary files on the host by supplying parent-directory segments in the filename form field with no path containment check. Attackers can register an...

EUVD-2026-56851

XAgent contains a path traversal vulnerability in the workspace file endpoint that allows self-registered or default-credential users to read arbitrary files on the host by supplying parent-directory segments in the filename form field with no path containment check. Attackers can register an...

CVE-2026-72713 XAgent Path Traversal Arbitrary File Read via /workspace/file

XAgent contains a path traversal vulnerability in the workspace file endpoint that allows self-registered or default-credential users to read arbitrary files on the host by supplying parent-directory segments in the filename form field with no path containment check. Attackers can register an...

PT-2026-70827

XAgent contains a path traversal vulnerability in the workspace file endpoint that allows self-registered or default-credential users to read arbitrary files on the host by supplying parent-directory segments in the file name form field with no path containment check. Attackers can register an...

CVE-2026-14891 Nomad vulnerable to sandbox escape in Docker task driver

HashiCorp Nomad and Nomad Enterprise are vulnerable to a sandbox escape in the Docker task driver that may allow a job submitter to bind-mount a host path into a container even when volume bind mounts are disabled, potentially leading to reading and writing files on the host. This vulnerability,...

CVE-2026-12539

Docker Sandboxes sbx blocks ICMP egress with an authorizer applied only at network-creation time, and does not re-apply it to networks rebuilt from disk when the Docker daemon restarts, so a restart-surviving sandbox forwards ICMP to arbitrary hosts. A workload inside a sandbox, which the threat...

CVE-2026-12539 Docker Sandboxes ICMP egress restriction bypass after daemon restart

Docker Sandboxes sbx blocks ICMP egress with an authorizer applied only at network-creation time, and does not re-apply it to networks rebuilt from disk when the Docker daemon restarts, so a restart-surviving sandbox forwards ICMP to arbitrary hosts. A workload inside a sandbox, which the threat...

CVE-2026-12539 Docker Sandboxes ICMP egress restriction bypass after daemon restart

Docker Sandboxes sbx blocks ICMP egress with an authorizer applied only at network-creation time, and does not re-apply it to networks rebuilt from disk when the Docker daemon restarts, so a restart-surviving sandbox forwards ICMP to arbitrary hosts. A workload inside a sandbox, which the threat...

MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills

AI coding agents such as Claude Code and Gemini CLI increasingly extend themselves with third-party skills: markdown packages bundling natural-language instructions, executable scripts, and tool permissions. Because a skill is at once code and agent-facing instruction, it introduces a supply chai...

vulnhunt-agent

Vulnerability Hunting Agent An LLM agent that reads code,...

OpenClaw Encryption Problem Vulnerability

OpenClaw is openclaw open source an intelligent artificial assistant. OpenClaw suffers from a cryptographic issue vulnerability that stems from the use of SHA-1 hashed Docker and browser sandbox configurations of the sandbox identifier cache key, which can be exploited by an attacker to enable...

EUVD-2026-9925

OpenClaw versions prior to 2026.2.15 use SHA-1 to hash sandbox identifier cache keys for Docker and browser sandbox configurations, which is deprecated and vulnerable to collision attacks. An attacker can exploit SHA-1 collisions to cause cache poisoning, allowing one sandbox configuration to be...

CVE-2026-28479

OpenClaw versions prior to 2026.2.15 use SHA-1 to hash sandbox identifier cache keys for Docker and browser sandbox configurations, which is deprecated and vulnerable to collision attacks. An attacker can exploit SHA-1 collisions to cause cache poisoning, allowing one sandbox configuration to be...