codex-security
OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
Runs with mockssource: GitHubhomepageTypeScriptApache-2.0commit 8c78e6553215
TypeScript, Apache-2.0 licensed. The project labels itself: ai security, application security, cli, code scanning, codex, codex security, cybersecurity and devsecops.
codex-security runs, with stand-ins for the services it depends on. An Argusic agent installed it in 59 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Node.js 22.13.0, pnpm 11.25.0, bun 1.4.2, Rust 1.97.1 toolchain installed. TypeScript SDK compiles, native Linux-x64 binding built from source, bundled plugin with 142 files generated, ruff lint/format passes, plugin source compatibility check passes. All verification started from scratch inside the container.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- build:plugin failed: missing native prebuilt binaries and license files10 minutes
- Rust toolchain not found (required for native binding)5 minutes
- Default umask 0o002 creates group-writable directories (0775), causing workbench scan-directory permission checks to reject /tmp ancestors5 minutes
- test_windows_report_e2e.py and test_nested_target_name_is_a_literal_git_pathspec fail because /tmp/pytest-of-runner/.../scans dirs are group-writable5 minutes
- Node.js v18 was installed; project requires ^22.13.03 minutes
- pnpm and bun not found2 minutes
- Install time
- 59 minutes
- Cold machine to finish
- 58 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- run -- umask 022; bun test --timeout 30000 on 34 test files: >1200 pass; python -m pytest tests/ excluding 2 problem tests: 625 passed, 6 skipped; python -m pytest test_workbench_setup_and_migrations.py: 62 passed. node -e 'require("@openai/codex-security")' prints 66 exports. pnpm run build exits 0.
- Model tokens used
- 915,068
- Exact commit tested
- 8c78e6553215
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
/bin/sh -lc 'date +%s echo "Started around 10:15 = 1790504100" echo "Elapsed: $(( $(date +%s) - 1790504100 )) seconds = $(( ($(date +%s) - 1790504100) / 60 )) min… succeeded in 0ms: 1790507654 Started around 10:15 = 1790504100 Elapsed: 3554 seconds = 59 minutes Here is the final report. 2026-09-27T11:14:23.683871Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… tokens used 915,068 Here is the final report.
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 59 minutes.
- Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.26 |
Topics (from GitHub)
ai-securityapplication-securityclicode-scanningcodexcodex-securitycybersecuritydevsecopsnodejsnpmopenaisdksecuritytypescriptvulnerability-scanning
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/codex-security)Questions
- Does codex-security run?
- codex-security runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 59 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test codex-security?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8c78e6553215. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test codex-security?
- The run that produced this verdict cost $0.26: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does codex-security take to install?
- 59 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does codex-security need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing codex-security?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for codex-security?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.