Security Audit Skill
Cloudflare's security-audit skill — turns your coding agent into a multi-phase auditor with independently verified findings, MIT
Codex Security — проект с открытым исходным кодом из категории «Инструменты разработчика» от openai (openai/codex-security на GitHub). У него 12 157 звёзд на GitHub и 965 форков, он распространяется по лицензии Apache-2.0 и последний раз обновлялся на GitHub 12 ноября 2026.
OpenAI's security scanner for Codex — find, validate and patch vulnerabilities from the CLI, SDK or GitHub Action, Apache-2.0
Install the package globally with npm — you need Node.js 22.13+ or 24/26 and Python 3.10+.
Log in once so the CLI can run scans against your account or API key.
Run a scan from the repository directory and read the saved Markdown report.
Ask for a patch for a finding, or verify a fix you already made.
Inside Codex, from the cs CLI, from the TypeScript SDK, or as a GitHub Action in CI.
Findings are validated before they reach you, patches are generated, and fixes are verified.
Deep mode repeats standard scans and returns deduplicated findings.
Drafts SECURITY.md, saves threat models, and exports SARIF, JSON and CSV.
Preview scanner findings from other tools, save them locally or publish to Codex Security Cloud.
Install the package globally; cs and codex-security are the same command.
npm install --global @openai/codex-securityLog in once before your first scan.
cs loginScan the current repository and open the report at the REPORT path it prints.
cs scan .Two more from the same shelf: Security Audit Skill — Cloudflare's security-audit skill, and claude-code-security-review — An AI-powered security review GitHub Action using. Browse every Dev Tools tool in the catalogue to compare the category.
OpenAI's security scanning tool: a CLI, TypeScript SDK, Codex plugin and GitHub Action that finds, validates, patches and verifies vulnerabilities.
Apache 2.0 code, but scans consume model usage — set an API key (OPENAI_API_KEY or CODEX_API_KEY) or sign in with Codex.
A saved Markdown report with findings, source evidence, severity, and the coverage limits of what was checked.
Yes — cs scan with --diff origin/main scans committed changes, and --path limits the scan to selected folders.
It can import third-party scanner findings too, so it works alongside existing tools rather than only replacing them.
Cloudflare's security-audit skill — turns your coding agent into a multi-phase auditor with independently verified findings, MIT
An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities.
Autonomous coding agent available as an SDK, IDE extension and CLI assistant
OpenAI's lightweight coding agent that runs locally in your terminal
AI coding agent skills for KiCad electronics design. Works with Claude Code and OpenAI Codex. Analyze schematics, review PCB layouts, EMC pre-compliance, SPI…
Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Discord, LINE, WeChat …
Другие проекты из категории «Инструменты разработчика» с наибольшим числом звёзд в каталоге LibreAI — реалистичный список альтернатив, если Codex Security вам не подходит.
The open source coding agent
The model-definition framework behind modern AI — thousands of pretrained transformers for text, vision, and audio.
Anthropic's agentic coding tool that lives in your terminal and works across your whole codebase
Cross-platform desktop all-in-one manager for Claude Code, Codex, OpenCode and other coding agents
OpenAI's lightweight coding agent that runs locally in your terminal
Соседние проекты из категории «Инструменты разработчика» в каталоге, ближайшие по числу звёзд к Codex Security — продолжайте изучать полку по обе стороны от него.
Code-search MCP for Claude Code: make your entire codebase the context for any coding agent.
Expose your FastAPI endpoints as Model Context Protocol tools - with authentication - in a few lines of code.
Axolotl — free, open-source LLM fine-tuning framework: LoRA, QLoRA and expert-parallel training, Apache-2.0
The audit skill from shadcn — your best model audits the codebase, cheaper models execute the plans, MIT
Your AI trading terminal assistant for US stocks, commodities, forex, and crypto.
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly wit…
Бесплатно и открыто — забирайте исходный код, ставьте звезду репозиторию и начинайте создавать.