Skip to content
IonWarpTry for free
Codex Security

Add Security Review
to your Codex pull requests.

OpenAI's Codex Security scans a repository for vulnerabilities. IonWarp reviews pull requests for the security holes they add.

sentry#67876
GitHub OAuth Security Enhancement
src/sentry/integrations/github/integration.pysentry #67876
IonWarp caught it Greptile, CodeRabbit and Cursor Bugbot missed it
IonWarpbotcommented on line 402

P2OAuth `state` is the deterministic pipeline signature, so the callback's CSRF binding is void · Security Review

When the user is sent to GitHub, `state` is set to `pipeline.signature`, which is `md5_text(*pipe_ids).hexdigest()` over the pipeline view class names (sentry/pipeline/base.py). It is a public constant — the PR's own test hard-codes it (`state=9cae5e88803f35ed7970fc131e6e65d3`). On the callback (`.../extensions/github/setup/`, served by PipelineAdvancerView with `auth_required=False, csrf_protect=False`) the check `request.GET.get("state") != pipeline.signature` therefore always passes for anyone who computes the constant. The established sibling, `OAuth2CallbackView`, instead uses `secrets.token_hex()` bound into pipeline state and compares against `pipeline.fetch_state("state")`. Consequence: an attacker completes GitHub's authorize step for their own account to obtain a `code`, then gets a victim who has an in-progress GitHub integration pipeline to load `.../extensions/github/setup/?code=<attacker code>&state=9cae5e88...&installation_id=<attacker installation>`. The victim's pipeline binds `github_authenticated_user` to the attacker, and because the supplied installation's `metadata["sender"]["login"]` is also the attacker, the new match check passes and the attacker's GitHub installation is linked into the victim's Sentry organization (login/CSRF on the OAuth callback).

Suggested change
             state = secrets.token_hex()             pipeline.bind_state("state", state)

MediumKnown issue in the Security Review benchmark · caught by DeepSeek V4.1 FlashSee the graded case

What Codex Security does, and what a pull request security review adds

Codex Security is OpenAI's application security agent.[1] It scans a repository, ranks likely vulnerabilities and tries to reproduce each one in a clean container; you review any patch before it becomes a draft pull request.[2]

IonWarp's Security Review reads one pull request before it merges. On 13 benchmark pull requests, DeepSeek V4.1 Flash, the model it runs, found 10 of 18 known security issues for about 6 cents a review; the Qodo app scored highest, an F1 of 73.3% to 62.5%.[3] What a security code review checks. Anthropic's pull request check is Claude Code security review.

A security hole three review apps missed

  • A CSRF check that checked nothing

    In Sentry #67876 the GitHub OAuth state was the pipeline's fixed signature, the same for every user, so the CSRF check did nothing. DeepSeek V4.1 Flash flagged it. Bugbot, CodeRabbit and Greptile missed it, and so did GLM 5.3 Flash, the benchmark's top model.[4]

    Security ReviewOn Starter, Pro and Max

IonWarp and Codex Security

OpenAI facts are from its Codex Security documentation, read on 2026-10-04; numbered notes link to each page.

CriterionIonWarpCodex Security
What it isA security reviewer in a GitHub app; the planner adds it to the pull requests that need itAn application security agent that helps teams find, confirm and fix vulnerabilities[1]
What it readsA pull request's changes and the code around themA repository or a folder, a pull request or branch before merge, or the new commits it monitors[1][2]
What it returnsFindings on the pull request with a severity, the attack path, a suggested fix and an AI fix promptRanked findings with criticality, validation evidence, remediation guidance and a proposed patch when one is available[2]
Where it runsIonWarp's hosted serviceThe Codex app, the open-source CLI and SDK, or Codex cloud for connected GitHub repositories[1][5]

Security Review on the benchmark

ModelF1PrecisionRecall$ per reviewMedian time
DeepSeek V4.1 FlashThe model it runs62.5%71.4%55.6%$0.065m 56s
GLM 5.3 FlashA failed review retries on it · best on this benchmark66.7%83.3%55.6%$0.011m 38s

On this benchmark GLM 5.3 Flash scored higher than DeepSeek V4.1 Flash (66.7% F1 against 62.5%). Why IonWarp runs DeepSeek V4.1 Flash: in a trial of our specialist reviewers on production pull requests on 23 September 2026 it filed about as many findings per review as GLM 5.3 Flash at high effort (0.93 against 1.02) for a third of the cost ($0.039 against $0.125), and 3 of its 64 findings were refuted. The benchmark ran GLM 5.3 Flash at low effort.

Measured on the same 13 open-source pull requests, with known issues. See the benchmark

IonWarp caught 9 issues Qodo, Greptile, CodeRabbit or Cursor Bugbot missed

Real IonWarp comments on open-source pull requests, graded against the benchmark's answer key.

Missed byQodo 3Greptile 5CodeRabbit 3Cursor Bugbot 6

2 of 9 · See the benchmark

db/migrate/20150818190757_create_embeddable_hosts.rbdiscourse-graphite #10
IonWarp caught it Cursor Bugbot missed it
IonWarpbotcommented on line 26

P2Migration interpolates site_settings value directly into INSERT SQL · Security Review

When the legacy 'embeddable_hosts' site_setting value contains a single quote or SQL metacharacter, `execute "INSERT ... VALUES ('#{h}', ..."` builds that value into raw SQL. The value is admin-controlled (not an untrusted actor), so no privilege gain, but a stray quote corrupts or fails the migration on upgrade.

CriticalKnown issue in the Security Review benchmark · caught by GLM 5.3 FlashSee the graded case

GLM 5.3 Flash is its best model on this benchmark; Security Review runs DeepSeek V4.1 Flash unless you pick another.

Pricing

Simple pricing for your whole team.

One workspace price with seats included. Credits pool across your team. Unlimited repos on every plan.

Starter

$0 /mo

Try AI PR review.

  • 2 reviewers
    • Code Review
    • Security Review
  • 3 seats included
  • 15,000 credits to start, then 5,000/mo
  • About 70 reviews to start, then about 25 a month
  • Unlimited repos
Get Started

Max

$149 /mo

Scale AI PR review.

  • +9 reviewers
    • UX Review
    • API Performance
    • Analytics Review
    • SEO Review
    • Changelog
    • CI/CD Performance
    • Plan Review
    • Repeat-Failure Learnings
    • SOC 2 Review
  • 10 seats included
  • +75,000 credits/mo
  • About 360 reviews a month
  • +$29/mo per added seat
  • Unlimited repos
  • Priority support
Choose Max
Enterprise

Custom reviewers + credits · GitHub Enterprise · SSO/SAML + audit logs · Custom security review + SLA

Contact us
FAQ

Frequently asked questions

What is Codex Security?

OpenAI's application security agent. It scans a repository, builds a threat model, tries to reproduce each likely issue in a clean container, and proposes patches that you review before opening a draft pull request.

Is Codex Security the same as Codex code review?

No. Codex code review posts a review on a pull request when you ask for one or turn on automatic reviews. Codex Security is a separate security agent that scans repositories and commits and tries to reproduce what it finds.

Can I use IonWarp next to Codex Security?

Yes. Codex Security scans and validates across the repository; IonWarp's Security Review comments on the pull requests whose changes need it. Both work on the same GitHub repositories.

Which plans include the security reviewer?

Security Review runs on Starter, Pro and Max. Starter is free for 3 seats with 15,000 credits on signup.

Sources

  1. Codex SecurityOpenAI · read
  2. Codex Security: Cloud FAQOpenAI · read
  3. The security review benchmark: 13 pull requests, 18 known issues (release of 2026-09-24)IonWarp benchmark · read
  4. getsentry/sentry #67876 (OAuth state), graded security findingsIonWarp benchmark · read
  5. openai/codex-securityOpenAI on GitHub · read