# Researchers hacked OpenAI through a malicious image

*Published on: Fri, 18 Sep 2026 15:34:36 GMT*

Researchers hacked OpenAI through a malicious image

They found a bug in how OpenAI’s forum processed HEIC images. Uploading a crafted image gave them control over the forum server.

From there, a flaw in OpenAI login let them access employee ChatGPT and Codex accounts, then reach an internal GitHub repo.

Claude Opus 5 helped build the exploit within hours.

---
[Back to home](https://alexgetman.com/) | [Read article](https://alexgetman.com/posts/432/researchers-hacked-openai-through-a-malicious-image/)