# Vercel launches Security Review, an AI agent that audits every code change

> Original title: I've been looking forward to this day, because Vercel has an internal security agent that is **astonishingly effective** (lovingly called...

- Source: Guillermo Rauch
- Published: 2026-11-03T21:45:04.000Z
- Bad Influence: https://badinfluence.news/items/m2wm2sxmqr2yqekcm7hhavvf7
- Original: https://x.com/rauchg/status/2117734833824948373

## Summary

Vercel launches Security Review in public beta, an internal security agent that audits every line of code automatically, and the company says it can be enabled on any repo whether hosted on Vercel or not. Vercel Agent can ship fixes in one click after each review. Vercel says the agent catches issues other agents miss and was built entirely by its own security team.

## Post

I've been looking forward to this day, because Vercel has an internal security agent that is **astonishingly effective** (lovingly called @𝚑𝚊𝚌𝚔𝚎𝚛). Every single line of code gets audited, automatically.

You can now get the same power. Just enable it on all your repos (this product works whether you host on Vercel or not) and your peace of mind will increase tremendously. You'll see it catch things that every other agent misses.

Why: you cannot just bank on your engineers having a skill installed, prompting "please make secure", or rolling the weights' dice that the code is good out of the gate.

The other cool thing about this is that this was entirely developed by our security team. A lot of companies out there are probably in a mad rush right now trying to staff up. If you wanted to 'download a security team' as software, this is the closest you get today.

## Quoted post @vercel

> Today we are launching Vercel Security Review in public beta.
> 
> Run vulnerability reviews on every push, and ship fixes in one click with Vercel Agent.
> 
> Read the blog → https://vercel.com/blog/vercel-security-review

https://x.com/vercel/status/2117726156992753721