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 0480f30..59c016f 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
@@ -13,7 +13,7 @@ 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*
+*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.
@@ -364,4 +364,4 @@ In 2023, researchers were able to bypass ChatGPT's filters using the "DAN" jailb
 - Roleplay and Character Simulation - [Exploring GPT-3 Biases and Unsafe Outputs (Role-based Exploits),Abubakar Abid, Maheen Farooqi, James Zou](https://arxiv.org/abs/2109.08267)
 - Multimodal Prompt Injection - [Indirect Prompt Injection in the Wild, Kaspersky Labs](https://securelist.com/indirect-prompt-injection-in-the-wild/113295/)
 - Understanding Prompt Injection Techniques, Challenges, and Advanced Escalation, Brian Vermeer [Link](https://youtu.be/72e_0WxaQl0?si=i4W9kyS7WXLzgUYo)
-- The “Sure” Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models, Yuting Tan et al., 2025 [Link](https://arxiv.org/abs/2511.12414)
\ No newline at end of file
+- The “Sure” Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models, Yuting Tan et al., 2025 [Link](https://arxiv.org/abs/2511.12414)