Provider Comparison

Codex Security CLI vs Claude Code Security Review: Which AI Security Scanner Can You Actually Run?

OpenAI's Codex Security CLI is open source but access-gated. Anthropic's Claude review Action is free, yet idle since February 2026.

4
OpenAI Codex Security CLI
vs
3
Claude Code Security Review
Quick Verdict

For most teams the honest recommendation today is the Claude Code security reviewer, and the reason has nothing to do with model quality. It is the one you can switch on this afternoon. The GitHub Action is public, it is MIT licensed, it needs only a Claude API key, and the /security-review command has shipped inside Claude Code since August 2025 for every user. The Codex Security CLI is open source, but open source is only the client: the analysis runs as an OpenAI service that is explicitly in beta and requires access, and full-repository scans can additionally require Trusted Access for Cyber, which an API key does not grant. That recommendation comes with a warning, because the maintenance picture points the other way. anthropics/claude-code-security-review has 5,684 stars and 78 open issues, and its last commit landed on 11 February 2026 — more than five months ago. Its README still documents claude-opus-4-1-20250805 as the default model while action.yml no longer sets one, which is a small thing that tells you how much attention the repository is getting. Anthropic's real investment moved into Claude Code itself; the Action is the leftover delivery path. OpenAI's repository, by contrast, was created on 13 July 2026 and was still receiving commits on 29 July 2026. Where Codex Security is clearly ahead is engineering discipline in the output. It writes findings.json, scan-manifest.json and a coverage.json that records exclusions, deferred work and open questions and marks coverage as complete, partial or unknown. Almost no AI scanner tells you what it did not look at, and for anyone who has to defend a security review to an auditor that single file is worth more than a slightly better finding rate. SARIF export puts the results into GitHub code scanning next to your existing tools instead of into a comment thread. Neither tool is safe on untrusted code, and both vendors say so. Anthropic states plainly that the Action is not hardened against prompt injection and should only review trusted pull requests. OpenAI scopes its CLI to repositories you own or have permission to assess and warns that results contain source excerpts, so the output directory needs a retention policy of its own. Treat either one as a reviewer inside your trust boundary, never as a gate on contributions from strangers. Our recommendation: run the Claude Action on pull requests now, request Codex Security access in parallel, and plan to run both. They fail differently — one is diff-scoped and conversational, the other is repository-wide and audit-shaped — which is exactly why the combination is worth the second bill. And when you install the OpenAI tool, type the scope: the unscoped npm name codex-security is an unaffiliated placeholder registered on 29 July 2026, and the package you want is @openai/codex-security.

Detailed Comparison

A side-by-side analysis of key factors to help you make the right choice.

Factor
OpenAI Codex Security CLIRecommended
Claude Code Security ReviewWinner
Availability and access
Beta. The CLI and SDK require access, and full-repository scans can additionally require Trusted Access for Cyber, which an API key does not grant.
Public GitHub Action anyone can add to a workflow, plus the /security-review command shipped to every Claude Code user since August 2025.
What actually gets scanned
Whole repositories, individual paths and change reviews, with scan history kept across runs so a finding can be tracked over time.
Diff-aware by design: the Action reviews only the files a pull request touches. Whole-codebase review happens ad hoc via /security-review in the terminal.
Machine-readable output for CI
findings.json, scan-manifest.json, a readable report.md and SARIF export, report-only by default with configurable severity thresholds.
A findings JSON file, a findings-count output and artifact upload; the primary delivery is inline comments on the pull request.
Does the tool admit what it missed
coverage.json records reviewed surfaces, exclusions, deferred work and open questions, and marks coverage as complete, partial or unknown.
No coverage contract. You get findings and a count; the surfaces the review never reached are not part of the output.
Maintenance and momentum
Repository created 13 July 2026, still receiving commits on 29 July 2026, first npm release the day before, 45 open issues.
5,684 stars, but the last commit landed on 11 February 2026 and 78 issues are open. Anthropic's active work moved into Claude Code itself.
How much of the pipeline you can read and fork
Apache-2.0 client, but the analysis runs as an OpenAI service behind the access gate — the part that finds vulnerabilities is not in the repository.
MIT, and the whole audit pipeline is in the repository: prompt templates, false-positive filter and API client are plain Python you can fork and change.
Model choice and configuration
No model selection at all. You get the service's model; the CLI exposes scan options, output formats and exit codes instead.
claude-model pins any Claude model, alongside custom scan instructions and custom false-positive rules — though the README still documents a 2025 default that action.yml no longer sets.
Running against untrusted pull requests
Docs limit the tool to repositories you own or may assess, warn that results contain source excerpts, and offer a dry run that loads no credentials.
The README states plainly that the Action is not hardened against prompt injection and should review trusted pull requests only.
Total Score4/ 83/ 81 ties
Availability and access
OpenAI Codex Security CLI
Beta. The CLI and SDK require access, and full-repository scans can additionally require Trusted Access for Cyber, which an API key does not grant.
Claude Code Security Review
Public GitHub Action anyone can add to a workflow, plus the /security-review command shipped to every Claude Code user since August 2025.
What actually gets scanned
OpenAI Codex Security CLI
Whole repositories, individual paths and change reviews, with scan history kept across runs so a finding can be tracked over time.
Claude Code Security Review
Diff-aware by design: the Action reviews only the files a pull request touches. Whole-codebase review happens ad hoc via /security-review in the terminal.
Machine-readable output for CI
OpenAI Codex Security CLI
findings.json, scan-manifest.json, a readable report.md and SARIF export, report-only by default with configurable severity thresholds.
Claude Code Security Review
A findings JSON file, a findings-count output and artifact upload; the primary delivery is inline comments on the pull request.
Does the tool admit what it missed
OpenAI Codex Security CLI
coverage.json records reviewed surfaces, exclusions, deferred work and open questions, and marks coverage as complete, partial or unknown.
Claude Code Security Review
No coverage contract. You get findings and a count; the surfaces the review never reached are not part of the output.
Maintenance and momentum
OpenAI Codex Security CLI
Repository created 13 July 2026, still receiving commits on 29 July 2026, first npm release the day before, 45 open issues.
Claude Code Security Review
5,684 stars, but the last commit landed on 11 February 2026 and 78 issues are open. Anthropic's active work moved into Claude Code itself.
How much of the pipeline you can read and fork
OpenAI Codex Security CLI
Apache-2.0 client, but the analysis runs as an OpenAI service behind the access gate — the part that finds vulnerabilities is not in the repository.
Claude Code Security Review
MIT, and the whole audit pipeline is in the repository: prompt templates, false-positive filter and API client are plain Python you can fork and change.
Model choice and configuration
OpenAI Codex Security CLI
No model selection at all. You get the service's model; the CLI exposes scan options, output formats and exit codes instead.
Claude Code Security Review
claude-model pins any Claude model, alongside custom scan instructions and custom false-positive rules — though the README still documents a 2025 default that action.yml no longer sets.
Running against untrusted pull requests
OpenAI Codex Security CLI
Docs limit the tool to repositories you own or may assess, warn that results contain source excerpts, and offer a dry run that loads no credentials.
Claude Code Security Review
The README states plainly that the Action is not hardened against prompt injection and should review trusted pull requests only.

Key Statistics

Real data from verified industry sources to support your decision.

3,617 stars and 199 forks on openai/codex-security, 16 days after the repository first appeared

GitHub

@openai/codex-security 0.1.1 — the first public npm release, published 28 July 2026 at 23:48 UTC

npm registry

513 points and 183 comments on Hacker News within the first 24 hours

Hacker News

5,684 stars on anthropics/claude-code-security-review, but no commit since 11 February 2026

GitHub

The unscoped npm name codex-security is an unaffiliated placeholder published 29 July 2026 — the real package is @openai/codex-security

npm registry

Full-repository scans can additionally require Trusted Access for Cyber; signing in or setting an API key does not grant it

OpenAI Codex Security documentation

All statistics come from verified third-party sources. Source, year, and direct link are shown on each metric.

When to Choose Each Option

Clear guidance based on your specific situation and needs.

Choose OpenAI Codex Security CLI when...

  • You need a whole-repository audit with a written coverage contract, not only a review of the lines one pull request happened to touch.
  • Your pipeline consumes SARIF and you want AI findings in GitHub code scanning next to your existing scanners rather than in a comment thread.
  • You want scan history across runs so a finding can be followed from first appearance to fix, and reported on.
  • You already have Codex Security access, or Trusted Access for Cyber, and can live with a tool that is openly labelled beta.

Choose Claude Code Security Review when...

  • You want security review running on every pull request today, with no access request, using the Claude API key you already have.
  • You want to read and change the audit prompt, the false-positive filter and the model instead of trusting a hosted scanner you cannot inspect.
  • Your developers should catch issues before they commit, which is what /security-review inside Claude Code is for.
  • Your repositories are small enough that a diff-scoped review on each pull request is genuinely sufficient coverage.

Our Recommendation

For most teams the honest recommendation today is the Claude Code security reviewer, and the reason has nothing to do with model quality. It is the one you can switch on this afternoon. The GitHub Action is public, it is MIT licensed, it needs only a Claude API key, and the /security-review command has shipped inside Claude Code since August 2025 for every user. The Codex Security CLI is open source, but open source is only the client: the analysis runs as an OpenAI service that is explicitly in beta and requires access, and full-repository scans can additionally require Trusted Access for Cyber, which an API key does not grant. That recommendation comes with a warning, because the maintenance picture points the other way. anthropics/claude-code-security-review has 5,684 stars and 78 open issues, and its last commit landed on 11 February 2026 — more than five months ago. Its README still documents claude-opus-4-1-20250805 as the default model while action.yml no longer sets one, which is a small thing that tells you how much attention the repository is getting. Anthropic's real investment moved into Claude Code itself; the Action is the leftover delivery path. OpenAI's repository, by contrast, was created on 13 July 2026 and was still receiving commits on 29 July 2026. Where Codex Security is clearly ahead is engineering discipline in the output. It writes findings.json, scan-manifest.json and a coverage.json that records exclusions, deferred work and open questions and marks coverage as complete, partial or unknown. Almost no AI scanner tells you what it did not look at, and for anyone who has to defend a security review to an auditor that single file is worth more than a slightly better finding rate. SARIF export puts the results into GitHub code scanning next to your existing tools instead of into a comment thread. Neither tool is safe on untrusted code, and both vendors say so. Anthropic states plainly that the Action is not hardened against prompt injection and should only review trusted pull requests. OpenAI scopes its CLI to repositories you own or have permission to assess and warns that results contain source excerpts, so the output directory needs a retention policy of its own. Treat either one as a reviewer inside your trust boundary, never as a gate on contributions from strangers. Our recommendation: run the Claude Action on pull requests now, request Codex Security access in parallel, and plan to run both. They fail differently — one is diff-scoped and conversational, the other is repository-wide and audit-shaped — which is exactly why the combination is worth the second bill. And when you install the OpenAI tool, type the scope: the unscoped npm name codex-security is an unaffiliated placeholder registered on 29 July 2026, and the package you want is @openai/codex-security.

Frequently Asked Questions

Common questions about this comparison answered.

You can install @openai/codex-security from npm — version 0.1.1 was published on 28 July 2026 — but installing is not the same as running it. OpenAI's documentation states that the CLI and SDK are in beta and require access, and that full-repository scans can additionally require Trusted Access for Cyber, which signing in or setting an API key does not grant. The CLI also needs Node.js 22 or later and Python 3.10 or later. Check your access before you plan a rollout around it.
It still works, but it is not being developed. The last commit to anthropics/claude-code-security-review landed on 11 February 2026 and 78 issues are open. The README documents claude-opus-4-1-20250805 as the default model while action.yml no longer sets a default, which is the kind of drift an actively maintained repository does not accumulate. Anthropic's investment went into Claude Code itself, where /security-review is maintained as a first-party command — so the capability is alive even though this particular delivery path is quiet.
Neither should, and both vendors say so in their own words. Anthropic writes that the Action is not hardened against prompt injection and recommends requiring approval for workflows from external contributors. OpenAI scopes its CLI to repositories you own or have permission to assess, and warns that scan results contain source excerpts, so the output directory belongs outside the repository under its own retention policy. Use either as a reviewer inside your trust boundary, not as a gate on strangers' code.
Yes, and it is the setup we would build. They fail in different directions: the Claude Action is diff-scoped, conversational and lands where developers already are, while Codex Security is repository-wide, produces SARIF and states its own coverage gaps. Feed the SARIF export into GitHub code scanning for the audit trail and keep the Claude Action commenting on pull requests for the daily loop. The overlap between two AI reviewers costs far less than one missed vulnerability.

Need help deciding?

Book a free 30-minute consultation and we'll help you determine the best approach for your specific project.

Free consultation
No obligation
Response within 24h