---
title: "Discussion on \"Classifying Malicious Repositories With AI — And Doing It Safely\" | Hashnode"
description: "Discussion on \"Classifying Malicious Repositories With AI — And Doing It Safely\". Phishing repos begone!"
url: "https://hashnode.com/posts/classifying-malicious-repositories-with-ai/6a984203dd4207244c52a9bd"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Classifying Malicious Repositories With AI — And Doing It Safely](https://kevinhwang.dev/classifying-malicious-repositories-with-ai?utm_source=hashnode&utm_medium=feed)

Phishing repos begone!

Sep 2 · 7 min read · kevinhwang.dev  
Read the article

-   [#ai](https://hashnode.com/tag/ai)
-   [#llm](https://hashnode.com/tag/llm)
-   [#security](https://hashnode.com/tag/security)
-   [#docker](https://hashnode.com/tag/docker)

## Written by

[Kevin Hwang](https://hashnode.com/@kevinhwang)

@kevinhwang

  
[View profile](https://hashnode.com/@kevinhwang)

Señor Vibe Coder

## Responses 1

Markdown supported · ⌘↵ to post

[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