Agent skill · security · aradotso
openai-codex-security
OpenAI Codex Security CLI and SDK for AI-powered vulnerability scanning, validation, and automated security fixes in codebases
Why this skill is useful
Adds a CLI and SDK for automated security scanning and vulnerability remediation that the AI cannot generate on its own.
What it needs
Requires node installed locally. Requires openai account access. About 5k tokens when loaded. Last updated 2026-08-04. 11 stars on the source repository.
What this skill does
OpenAI Codex Security Skill by ara.so — Security Skills collection OpenAI Codex Security is an AI-powered CLI and TypeScript SDK that finds, validates, and fixes security vulnerabilities in your codebase. It leverages OpenAI's models to perform intelligent code scanning, vulnerability detection, and automated security remediation. Installation Requires Node.js 22.13.0+ (22.x), 24.x, or 26.x; Python 3.10+; and access to Codex Security. For global CLI access: Authentication Interactive Login (Local Development) This stores credentials in Codex's credential home or system keyring for persistent access. API Key (CI/CD) Set environment variables instead of interactive login: Environment API keys take precedence in non-interactive environments and are never persisted. Credential Selection If both ChatGPT sign-in and API key are available: To make ChatGPT sign-in the default: CLI Commands Basic Scan Scan current directory: Scan specific directory: Advanced Scanning Options Use specific model with higher effort: Available effort levels: low - Quick scan, fewer checks medium - Balanced (default) high - Thorough scan, maximum coverage Scan Output Scan history is stored in the Codex Security workbench state directory. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/openai-codex-security