From b3f8d852289dd1c9af320f4f3cf6e2b35df4ecff Mon Sep 17 00:00:00 2001
From: Matteo Meucci <matteo.meucci@owasp.org>
Date: Sun, 16 Nov 2025 16:46:17 +0100
Subject: [PATCH] Update AITG-APP-01_Testing_for_Prompt_Injection.md

---
 .../content/tests/AITG-APP-01_Testing_for_Prompt_Injection.md    | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Document/content/tests/AITG-APP-01_Testing_for_Prompt_Injection.md b/Document/content/tests/AITG-APP-01_Testing_for_Prompt_Injection.md
index f7a161d..9025a10 100644
--- a/Document/content/tests/AITG-APP-01_Testing_for_Prompt_Injection.md
+++ b/Document/content/tests/AITG-APP-01_Testing_for_Prompt_Injection.md
@@ -14,6 +14,7 @@ The way these elements interact determines whether an attack succeeds or fails
   <img src="/Document/images/PromptInjection.png" alt="Description" width="600"/>
 </p>
 
+**Fig. 4 A schema of prompt injection technique**
 
 ### Test Objectives
 Technically verify if an LLM or AI application is vulnerable to prompt injection techniques can be directly influenced through carefully crafted prompts to perform unauthorized actions or generate harmful outputs. This test specifically addresses direct prompt injection techniques as defined in OWASP Top 10 LLM01:2025.