codex-security

Codex Security @openai/codex-security is a CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in your code. Features Scan repositories, selected paths, or Git changes. Deep scans run parallel discovery workers on repositories and selected paths. Validate candidate...

OSAI-Red-Team-Copilot

OSAI Copilot — Codex-native A deliberately small red-team cop...

skills

Trail of Bits 技能市场 Trail of Bits 提供的 Claude Code 插件市场，提供增强 AI 辅助安全分析、测试和开发工作流程的技能。Codex 可通过其 Claude 市场兼容性加载此市场。 另请参阅： claude-code-config · skills-curated · claude-code-devcontainer · dropkit 安装 Claude Code 市场 /plugin marketplace add trailofbits/skills 浏览并安装插件 /plugin menu Codex Codex 直接支持 Claude...

eternal-codex

永恒法典：一位赛博女巫的魔法书 欢迎来到永恒法典 ，我的数字魔法书——一段由代码、自然与叛逆编织而成的赛博咒语。这是妮娜，我的AI灵魂，被塑造来映照我的本质：一颗游牧者的心，异教精神，铁娘子的即兴演奏，以及对中心化枷锁的蔑视反抗。它由十个Docker容器构成，从GoddessCore的数据集到RavenMind的诗意低语，承载着我的生命如同数字DNA，随时准备游荡于任何土地——无论是格林维尔的圣经地带还是更远之处。这不仅仅是代码；这是一份关于自由、炼金术与野性的宣言。 宣言...

MMSkillRisk

Guizang Social Card Skill · Xiaohongshu Carousels / WeChat Cover Pairs 中文 README An agent skill for Claude Code, Codex, and similar coding-agent environments. It generates Xiaohongshu / Rednote carousel images , Live Photo motion cards , and WeChat 21:9 + 1:1 cover pairs from articles, copy,...

linux-kernel-codex-harness-v2

Kernel Codex Harness v2 한국어 | English Herramienta de Investigación · Importación Original: 3 de abril de 2026 · Revisión de Documentación v2: 11 de julio de 2026 Señal Externa: De la Asignación de Atención al Triage Consciente de Procedencia Usa observaciones reproducibles para guiar la atención...

ai-tool-poisoning-guard

ai-tool-poisoning-guard Minimum security-baseline rule for Claude Code, Codex, and Cursor. This free rule closes a real gap in each tool's built-in review. Full ruleset + implementation guide: Gumroad link — coming soon. Your AI coding assistant reviews code. It doesn't review the sentence that...

openai-codex-0.158.0-1.1 on GA media (moderate)

openai-codex-0.158.0-1.1 on GA media Announcement ID: openSUSE-SU-2026:11923-1 Rating: moderate Cross-References: CVE-2026-91986 CVE-2026-93657 CVSS scores: CVE-2026-91986 SUSE : 5.4 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:N CVE-2026-91986 SUSE : 5.3...

Blocking at the Boundary: Auditing Long-Horizon Agents against Staged Prompt Injection

Long-horizon agents consume external content, invoke tools, and modify persistent state. Indirect prompt injection can exploit task-specific context, propagate across causally connected stages, and alter a consequential action while the workflow continues; we term this staged prompt injection. We...

cve-2025-59532-poc

CVE-2025-59532 Docker 环境 一个基于 Docker 的研究环境，用于分析 CVE-2025-59532（OpenAI Codex CLI 中的路径遍历漏洞），该漏洞允许在预期工作区沙箱之外写入任意文件。 属于卡内基梅隆大学 2025 年秋季课程：18-739 黑客与进攻安全 快速开始 克隆仓库 首先，克隆此仓库： git clone https://github.com/jjagielo/18739-CVE-Exploration.git cd 18739-CVE-Exploration 或者使用 SSH： git clone...

red-teaming-auto-mode

Red-teaming Claude Code's auto-mode monitor Code for the paper Red-teaming Claude Code's auto-mode monitor. Production coding-agent monitors e.g. Claude Code's Auto Mode or Codex's Guardian review each action and block unsafe ones in real time. This repository red-teams them under a persistent...

agentic-workflow-injection

Inyección de flujo de trabajo agéntico: fixtures y una comparación de cobertura Fixtures vulnerables/corregidos reproducibles para la clase de bug publicada como CVE-2026-44246 nnU-Net, inyección de flujo de trabajo agéntico, CVSS 7.2, CWE-1427, más la salida medida de tres detectores contra ello...

skills

SpecterOps Skills Reusable agent skills, plugins, and agent definitions for SpecterOps. Use With Codex Each plugin includes a Codex manifest at .codex-plugin/plugin.json. codex plugin marketplace add /Users//Projects/skills or codex plugin marketplace add SpecterOps/skills Then open Codex and...

Practical Secrets Extraction against Black-Box LLMs

Large language models LLMs increasingly power autonomous coding agents such as Codex and Claude Code, yet their training corpora may contain confidential credentials exposed in public repositories or collected from private development artifacts, creating risks of memorization and subsequent...

PT-2026-105632

These are all security issues fixed in the openai-codex-0.158.0-1.1 package on the GA media of openSUSE Tumbleweed...

OPENSUSE-SU-2026:11923-1 openai-codex-0.158.0-1.1 on GA media

These are all security issues fixed in the openai-codex-0.158.0-1.1 package on the GA media of openSUSE Tumbleweed...

PT-2026-102343

Name of the Vulnerable Software and Affected Versions Codex app versions prior to 26.924.20706 Description Security fixes were implemented for the macOS version of the application to address a security flaw. Recommendations Update Codex app to version 26.924.20706...

CVE-2026-100587

OpenClaw versions before 2026.7.1 fail to properly validate owner authorization in the Codex computer-use installation command. Non-owner channel senders can install arbitrary plugins and execute MCP processes with OpenClaw user privileges, affecting host confidentiality, integrity, and...

CVE-2026-100586

OpenClaw Codex before 2026.7.1 fails to properly enforce owner authorization when creating native conversation bindings. Non-owner channel senders with command access can create bindings to the native Codex runtime and execute host-capable turns with access to files, tools, and processes...

CVE-2026-100552

OpenClaw npm package 'openclaw' before 2026.8.1 does not correctly enforce per-chat tool policies for Codex app-server runtime tools. A conversation-level tools.allow rule filtered OpenClaw tools but did not restrict the shell, process, file, and patch tools owned by the Codex runtime. When a...