Codex Security
by OpenAI
Official listing: built and published by OpenAI. More from OpenAI
Finds, validates and patches code vulnerabilities in repositories and Git changes, from the cs CLI, a TypeScript SDK, a GitHub Action or Codex.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Scan repositories
Use Codex Security to scan whole repositories, selected paths or Git changes for vulnerabilities: ‹what you need›
- Validate and patch findings
Use Codex Security to validate candidate findings: ‹what you need›
- Threat models and policies
Use Codex Security to draft SECURITY.md policies: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: developers.openai.com/codex/security
Call the API
Auth An API key from OpenAI
Its page: developers.openai.com/codex/security
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- CLIAPI
- Auth
- API Key
- Skills
- 3
Skills
Scan repositories
Scans whole repositories, selected paths or Git changes for vulnerabilities and returns deduplicated findings.
Validate and patch findings
Validates candidate findings, generates patches for them and verifies that existing fixes hold.
Threat models and policies
Drafts SECURITY.md policies and saves threat models of a project for later security review.