Ai-Security - Tag - My Personal Bloghttps://f0dh1l.github.io/blog/tags/ai-security/Ai-Security - Tag - My Personal BlogHugo -- gohugo.ioenbenhibafodhil@gmail.com (F0DH1L)benhibafodhil@gmail.com (F0DH1L)2025 F0DH1LSun, 05 Jul 2026 22:47:59 +0100Attacking LLMs Using Indirect Prompt Injectionhttps://f0dh1l.github.io/blog/posts/attacking-llms-using-indirect-prompt-injection/Sun, 05 Jul 2026 22:47:59 +0100benhibafodhil@gmail.com (F0DH1L)https://f0dh1l.github.io/blog/posts/attacking-llms-using-indirect-prompt-injection/I recently started learning more about LLM security, and one of the first techniques you come across is prompt injection, where a user crafts a malicious input to override the model’s instructions. Everyone knows about this one.

But there’s another technique called indirect prompt injection. It’s not new, it was first discovered and published in 2023, but not a lot of people know about it. The first paper to define and name this attack was “Not what you’ve signed up for” by Greshake et al., published at AISec @ CCS 2023. So I decided to research it, read the original paper, and build a small project to test these attacks.

]]>