---
title: "Comment by Julian Neagu on \"Classifying Malicious Repositories With AI — And Doing It Safely\" | Hashnode"
description: "ai agents make untrusted repos a much bigger problem now. even opening a project can expose the agent to stuff it should never trust"
url: "https://hashnode.com/posts/classifying-malicious-repositories-with-ai/6a984203dd4207244c52a9bd/comment/6a9ad6c8d26aaf5f85c58024"
---

[Discussion](https://hashnode.com/posts/classifying-malicious-repositories-with-ai/6a984203dd4207244c52a9bd)

Comment [Classifying Malicious Repositories With AI — And Doing It Safely](https://hashnode.com/posts/classifying-malicious-repositories-with-ai/6a984203dd4207244c52a9bd)

[Julian Neagu](https://hashnode.com/@julianneagulab)

[Sep 4](https://hashnode.com/posts/classifying-malicious-repositories-with-ai/6a984203dd4207244c52a9bd/comment/6a9ad6c8d26aaf5f85c58024)

ai agents make untrusted repos a much bigger problem now. even opening a project can expose the agent to stuff it should never trust