https://amylily1011.github.io/tags/prompt-injection/ Recent content in Prompt Injection on Amy Lily Hugo en-us This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. Mon, 06 Apr 2026 00:00:00 +0000 https://amylily1011.github.io/ai-security/same-model-different-answer/ Mon, 06 Apr 2026 00:00:00 +0000 https://amylily1011.github.io/ai-security/same-model-different-answer/ I asked three Claude interfaces the same prompt injection question. One gave me a full strategy guide. The other two drew the line at explanation. Same model — completely different behavior. Here’s what that reveals. https://amylily1011.github.io/ai-security/prompt-injection/ Thu, 26 Mar 2026 00:00:00 +0000 https://amylily1011.github.io/ai-security/prompt-injection/ I started a Hack The Box AI security lab with zero expectations. Three minutes later, I had leaked a secret key the model had been explicitly told never to reveal. Here’s what I learned — and why it matters if you build with LLMs.