# OpenAI Codex Security 21 Hacker News commenters recommended OpenAI Codex Security and 30 criticized it, November 2025 to November 2026. It was recommended in 4 of 13 months. **Verdict:** People recommend it for finding real vulnerabilities with few false positives and suggesting small, targeted fixes. Critics say long scans show little progress and access requires cyber registration. ## Why people recommend it - Finds real issues with few false positives (2 comments): "It found a real security issue in a project of mine, with very few false-positives." ([source](https://news.ycombinator.com/item?id=48642499)) "Codex Security and 5.5/5.6 are still very good finding vulnerable code" ([source](https://news.ycombinator.com/item?id=48642284)) - Built for repo-wide security workflows (3 comments): "It seems like openai/codex-security could simplify a lot of that, or at least provide a version of Codex that's purpose-built for security workflows." ([source](https://news.ycombinator.com/item?id=49090254)) "They are genuinely impressive at the repository level, but they run asynchronously." ([source](https://news.ycombinator.com/item?id=47400573)) "built for running security across many repos over time" ([source](https://news.ycombinator.com/item?id=49090447)) - Praised by early users (3 comments): "I turned it on just as an experiment and in less than a week it has now become essential to all of us." ([source](https://news.ycombinator.com/item?id=48241120)) "This looks great, thanks for open-sourcing it!" ([source](https://news.ycombinator.com/item?id=49090853)) "I've heard great reviews about this" ([source](https://news.ycombinator.com/item?id=49095792)) ## What people warn about - Long scans with little visible progress (4 comments): "the CLI output is not particularly interesting while the scan is running" ([source](https://news.ycombinator.com/item?id=49090634)) "its running now for over an hour in my Python code base without any feedback" ([source](https://news.ycombinator.com/item?id=49095372)) "its running now for over an hour in my Pythin code base without any feedback" ([source](https://news.ycombinator.com/item?id=49095377)) - Guardrails and cyber registration limit access (4 comments): "These ""guardrails"" make all of this borderline useless, and even pointless in a world with powerful open-weight models." ([source](https://news.ycombinator.com/item?id=49098014)) "They silently return an earlier model's results if they think you're redteaming/abusing with it." ([source](https://news.ycombinator.com/item?id=48470681)) "Allow only OpenAi key? Requires Cyber registration? Yes. Yes. Useless." ([source](https://news.ycombinator.com/item?id=49091286)) - Scans stop without final results (3 comments): "The partial output did contain some useful signal but I was disappointed to see it didn’t finish." ([source](https://news.ycombinator.com/item?id=49094162)) "it bailed before finishing. Unknown if I would get full results for $105 or $500." ([source](https://news.ycombinator.com/item?id=49096396)) "Charging users for a session that produced no final output is ridiculous." ([source](https://news.ycombinator.com/item?id=49094536)) - Unclear and high charges for scans (3 comments): "it bailed before finishing. Unknown if I would get full results for $105 or $500." ([source](https://news.ycombinator.com/item?id=49096396)) "Charging users for a session that produced no final output is ridiculous." ([source](https://news.ycombinator.com/item?id=49094536)) "It’s like they want to squeeze more money from you with the cyber crap" ([source](https://news.ycombinator.com/item?id=49097456)) ## Alternatives hackers recommend - [govulncheck](https://hackerapproved.com/p/govulncheck.md): 13 recommend - [Trivy](https://hackerapproved.com/p/trivy.md): 10 recommend - [cargo-vet](https://hackerapproved.com/p/cargo-vet.md): 8 recommend - [cargo-audit](https://hackerapproved.com/p/cargo-audit.md): 8 recommend - [Aikido Safe-Chain](https://hackerapproved.com/p/aikido-safe-chain.md): 7 recommend ## Cite as Hacker Approved, "OpenAI Codex Security", https://hackerapproved.com/p/codex-security/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).