A local proxy that lets Codex, Claude Code, Claude Desktop and Grok Build run any LLM provider.
openai/codex-security
A CLI and TypeScript SDK from OpenAI for scanning code for security vulnerabilities, validating findings, and generating fixes.
- Звёзды
- 11,135
- Форки
- 962
- Открытые issues
- 229
- Последний коммит
- 3 часа назад
Что это?
Codex Security is a CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in source code. It can scan a whole repository, selected paths, or only Git changes, with a deep mode that runs parallel discovery workers. Candidate findings can be validated, patches generated, and existing fixes re-verified.
Beyond scanning, it helps manage results: it drafts a SECURITY.md policy, saves threat models, deduplicates findings, assigns severity against a custom rubric, and suggests owners from source and Git history. Results can be imported from GitHub code scanning alerts and exported as SARIF, JSON, or CSV, or published to Linear or a findings service.
It runs locally with Node.js 22.13+ or 24/26 and Python 3.10+, can be used in GitHub Actions, CI, and containers, and supports OpenAI, Amazon Bedrock, OpenRouter, Fireworks AI, and Cheaper Inference as model providers.
Ключевые возможности
- 01Scans repositories, selected paths, or Git diffs, with a deep mode using parallel workers.
- 02Validates candidate findings, generates patches, and verifies existing fixes.
- 03Drafts SECURITY.md policies and saves threat models.
- 04Deduplicates findings and assesses severity against a custom rubric.
- 05Imports GitHub code scanning alerts and exports SARIF, JSON, or CSV.
- 06Runs in GitHub Actions, CI, and containers.
Сценарии использования
- Running scheduled or pull request security scans in GitHub Actions.
- Reviewing only the changes in a branch before merging.
- Scanning multiple repositories in a resumable bulk campaign.
- Exporting SARIF results to feed existing code scanning dashboards.
Темы
Частые вопросы
- Что такое codex-security?
- A CLI and TypeScript SDK from OpenAI for scanning code for security vulnerabilities, validating findings, and generating fixes. Codex Security is a CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in source code. It can scan a whole repository, selected paths, or only Git changes, with a deep mode that runs parallel discovery workers. Candidate findings can be validated, patches generated, and existing fixes re-verified.
- codex-security можно использовать бесплатно? Какая у него лицензия?
- codex-security распространяется с открытым исходным кодом под лицензией Apache-2.0. Перед использованием в коммерческих продуктах проверьте условия лицензии.
- codex-security всё ещё поддерживается?
- Активно поддерживается. Последний коммит в codex-security — 19 окт. 2026 г..
- Для чего можно использовать codex-security?
- Running scheduled or pull request security scans in GitHub Actions. Reviewing only the changes in a branch before merging. Scanning multiple repositories in a resumable bulk campaign. Exporting SARIF results to feed existing code scanning dashboards.
- Где скачать codex-security?
- Исходный код и инструкции по установке — на GitHub: https://github.com/openai/codex-security
Описание создано ИИ на основе README проекта. Статистика GitHub обновляется ежедневно.
Похожие проекты
MCP-сервер и CLI, с помощью которых AI-агенты анализируют нативные бинарные файлы, приложения Electron, сборки .NET и сайты.
A CLI tool for detecting hardcoded secrets such as passwords, API keys and tokens in git repos, files and stdin.
A Python CLI that uses LLMs such as Google Gemini, OpenAI, and Claude to orchestrate penetration-testing workflows around established security tools like nmap and nuclei.
A Python tool from Cisco that scans MCP servers, tools, prompts and source code for security threats using YARA rules, LLM analysis and Cisco AI Defense.
Open source AI-агент для программирования, работающий в терминале; также доступны desktop-приложение и два встроенных агента для разработки и планирования изменений.