Can OpenAI's GPT 4.1 Write Secure Code?

Snyk

Apr 21, 2025

In this video, I put OpenAI's latest model, ChatGPT-4.1, to the test to see if it can generate secure code. Can AI really help us write safer, bug-free applications? Or does it still fall into common security pitfalls like SQL injection, XSS, and insecure auth flows? Stay tuned to find out!

Use Snyk for free to find and fix security issues in your applications today! https://snyk.co/ugLYn

✍️ Resources ✍️

OpenAI GPT 4.1 Annoucement: https://openai.com/index/gpt-4-1/
GitHub Repository: https://github.com/clarkio/ai-code-security

⏲️ Chapters ⏲️

00:00 - Intro

00:17 - Prompt and results

03:28 - Running the app

04:03 - Fixing code

05:14 - Subscribe!

05:23 - Fixing final errors

05:37 - Running and using the app

06:09 - Security checking

08:56 - How does this compare to previous models?

09:40 - Summary

10:13 - Outro

⚒️ About Snyk ⚒️

Snyk helps you find and fix vulnerabilities in your code, open-source dependencies, containers, infrastructure-as-code, software pipelines, IDEs, and more! Move fast, stay secure.

Learn more about Snyk: https://snyk.co/ugLYl

📱 Connect with Us 📱

🖥️ Website: https://snyk.co/ugLYl
🐦 X: http://twitter.com/snyksec
💼 LinkedIn: https://www.linkedin.com/company/snyk
💬 Discord: https://discord.gg/devsecops-community-918181751526948884