Skip to main content
AdOpenFree logoPromote your productReach more potential users and drive product growth and revenue.Advertise
Favicon of Codex Security

Codex Security

Free Listing

Codex Security reviews code for vulnerabilities and reports evidence for investigating and fixing them. It can be used through Codex workflows or automated with the @openai/codex-security CLI and TypeScript SDK.

Visit openai/codex-security

Overview

Codex Security is OpenAI's security tooling for scanning application code, investigating findings, and reviewing fixes. It reports evidence to support vulnerability investigation and remediation, and can be used through Codex workflows or automated with the CLI and TypeScript SDK.

Key Features

  • Scans repositories, selected paths, or Git changes, with deep scans repeating standard scans and returning deduplicated findings.
  • Validates candidate findings, generates patches, and verifies existing fixes.
  • Drafts SECURITY.md policies and saves threat models for later review.
  • Browses saved scans and findings, identifies duplicates, assesses severity against a custom rubric, and suggests owners from source and Git history.
  • Imports third-party scanner findings and supports export as SARIF, JSON, and CSV, with tracking in Linear, Jira, or GitHub.
  • Automates scans across repositories or project components, including in CI and containers.

Use Cases

  • Scan a local repository interactively in Codex and work through findings.
  • Run repeatable terminal scans or add security checks to CI.
  • Run scans and handle results inside an application or developer tool with the TypeScript SDK.
  • Scan connected GitHub repositories in Codex cloud or monitor new commits with Codex Security Cloud.

Getting Started

  • For a first local scan, use the Codex Security plugin in the ChatGPT desktop app or Codex CLI.
  • Install the CLI globally with npm install --global @openai/codex-security, sign in with cs login, then run cs scan . from the repository directory.
  • When the scan completes, open the Markdown report at the REPORT path shown in the terminal.

Deployment & Requirements

  • CLI requires Node.js 22.13.0+ within 22.x, or Node.js 24.x or 26.x, and Python 3.10+; Python 3.10 also requires tomli.
  • Scans using OpenAI inference require Codex Security access; CI scans need OPENAI_API_KEY or CODEX_API_KEY set in the scan process environment.
  • Codex Security Cloud requires workspace access, a GitHub connection, and a compatible Codex cloud environment.

Before You Adopt

  • License: Apache-2.0. Review its terms before using, modifying, or distributing the project.

Comments

Sign in to leave a comment.

More like Codex Security

Favicon of Shannon

Shannon

Free ListingStars: 51.3K

Continuous agentic pentesting with proven exploits

Security Testing & Red Teaming

Shannon is an AI pentester for web apps and APIs that analyzes source code, identifies attack vectors, and executes real exploits. Keygraph adds continuous agentic pentesting per build, reporting findings only with working exploits.

Favicon of ADR

ADR

Free ListingStars: 2.1K

Enterprise security for AI agents

Security Testing & Red Teaming

ADR (Agentic AI Detection and Response) is an enterprise security system for AI agents. It discovers unsanctioned AI tools, observes agent activity, benchmarks defenses, and detects threats across employee-facing and customer-facing agents.

Favicon of ZeroLeaks

ZeroLeaks

Free ListingStars: 0.7K

Continuous red teaming for AI agents

Security Testing & Red Teaming

ZeroLeaks offers security testing for AI agents and LLM prompts. Hosted continuous red teaming attacks agents through tools, memory, credentials, and connected agents; the source-available CLI and TypeScript library test standalone prompts.