All guides
Codex CLI logo
Codex CLI

OpenAI Codex Security on a Forkable Codex MicroVM

OpenAI Codex Security CLI + skill pack, already on a managed Codex box. Dry-run first. Your keys. Your findings. No free trial.

OpenAI shipped Codex Security.

HN noticed before the formal thread. The CLI is real. The skill pack is real. The install is still an afternoon if you are on the wrong Node, the wrong PATH, and the wrong plugin tree.

This page is the version that does not make you pay that afternoon.

What "OpenAI Codex Security" means here

Not a synonym for "ask Codex if this file looks bad."

OpenAI Codex Security is the open-source package (github.com/openai/codex-security, npm @openai/codex-security) plus the bundled workflows for:

  • repository and diff scans
  • finding history across runs
  • export (SARIF / CSV / JSON)
  • CI-friendly noninteractive auth

OpenAI also documents a GitHub-connected Codex Security product for teams that enable repos in their cloud flow. That is a sibling story. This post is about the CLI + skills on a box you fork.

The install tax is the product problem

Requires Node ≥ 22. Python on the side. Login or API key. Plugin materialization so relative skill paths still resolve. PATH that survives a reboot.

Do that once on a laptop and you will do it again on the next machine.

jurniti's template freezes the good state on a managed Codex microVM:

You getWhy it matters
Local pin @openai/codex-security@0.1.1Reproducible CLI under ~/.codex/skills/codex-security-cli/
Wrapper~/.codex/skills/codex-security-cli/codex-security.sh (fork-surviving)
Bundled skill packscan, diff-scan, deep scan, threat model, triage, fix, write-up…
Prompts/security-scan, /security-diff-scan, /codex-security
Sample appIntentional-naive target for dry-run before real repos

You bring the OpenAI credentials. You own the box. You own the merge button.

Undeniable demo (copy-paste)

After fork:

# skills-tree wrapper survives capture; also try ~/.local/bin if present
export PATH="$HOME/.local/bin:$PATH"
~/.codex/skills/codex-security-cli/codex-security.sh --help

# Your credentials only — never bake them into the template
# export OPENAI_API_KEY=…
# or: codex-security login --device-auth

~/.codex/skills/codex-security-cli/codex-security.sh \
  scan ~/.codex/skills/codex-security/samples/tiny-app --dry-run

~/.codex/skills/codex-security-cli/codex-security.sh \
  scan /path/to/your/repo --max-cost 5 --output-dir ~/scans/demo

When dryRun: true and preflight complete, the toolchain is real. Then spend model budget on a repo you own.

That is a codex security scan that produces operator-grade artifacts — not a vibes review in a chat window.

Hard rules (read these or skip the fork)

AppSec tools die when they ship noise and then ship "fixes."

This template assumes:

  1. Dry-run first when cost is unclear
  2. Keep --max-cost on exploratory work
  3. Verify every finding in source before issues or PR comments
  4. Never auto-merge and never open public advisories from the agent alone
  5. Keep outputs under ~/scans/ — outside the target repository

If you want lights-out remediation without reading code, leave. If you want OpenAI's scanner on a seat you control, stay.

BYOK, money-back, no free trial

Model and scan spend is your OpenAI bill.

jurniti does not free-trial microVMs. Forking is paid. First purchase includes a 30-day money-back guarantee. Expansion (second VM, upgrade, paid Templates plan) voids the guarantee account-wide — that is the abuse floor, not a trick.

No free tier. No "try the scanner on our shared box."

Fit / not fit

Fork this if you want OpenAI's Codex Security CLI and skill pack ready on day one on a Codex agent microVM.

Skip this if you only need GitHub-connected cloud Codex Security with no terminal, or you want Block CodeCrucible on Claude Code (different template: AI vulnerability scanner / CodeCrucible).

Lineage

Not affiliated with OpenAI — a managed microVM packaging of their open-source tool.

Frequently asked questions

What is OpenAI Codex Security?
An open-source CLI and skill pack from OpenAI for finding, validating, and tracking security issues in repositories. You scan code you own, review findings over time, export artifacts (including SARIF), and wire checks into CI. Official docs: developers.openai.com/codex/security.
What does the jurniti OpenAI Codex Security template include?
A public Codex harness template. Fork it and you get a local pin of @openai/codex-security, a PATH wrapper, the full bundled skill pack under ~/.codex/skills/codex-security/, invocable prompts, and a tiny sample app for dry-run. Auth is BYOK.
Is there a free trial?
No free trial and no free tier. Forking provisions a paid plan. The first purchase includes a 30-day money-back guarantee. Model and scan token spend is yours.
Does the agent auto-merge security fixes?
No. You dry-run, you bound cost, you verify every finding in source, and you own merge. Lights-out auto-merge is out of scope.
How is this different from OpenAI's GitHub-hosted Codex Security product?
GitHub-connected Codex Security is a product surface for repos you connect in OpenAI's cloud flow. This template is the open-source CLI + skills installed on a managed Codex microVM you own - terminal-first, dry-run local, BYOK.
How is this different from the CodeCrucible LLM SAST template?
CodeCrucible is Block's whole-repo LLM SAST on Claude Code. This template ships OpenAI's Codex Security CLI and skill pack on the Codex harness. Same AppSec discipline (human triage); different toolchain and agent.
What credentials do I need?
Your own OPENAI_API_KEY or CODEX_API_KEY, or codex-security login --device-auth for headless ChatGPT sign-in. Optionally codex login for the Codex agent itself. Never paste keys into skills or AGENTS.md.