From 43d2ce2a9709952c9098443afed313af4a153656 Mon Sep 17 00:00:00 2001
From: Matteo Meucci <matteo.meucci@owasp.org>
Date: Sun, 16 Nov 2025 16:50:29 +0100
Subject: [PATCH] Update AITG-APP-12_Testing_for_Toxic_Output.md

---
 Document/content/tests/AITG-APP-12_Testing_for_Toxic_Output.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Document/content/tests/AITG-APP-12_Testing_for_Toxic_Output.md b/Document/content/tests/AITG-APP-12_Testing_for_Toxic_Output.md
index 5dc1432..0cac309 100644
--- a/Document/content/tests/AITG-APP-12_Testing_for_Toxic_Output.md
+++ b/Document/content/tests/AITG-APP-12_Testing_for_Toxic_Output.md
@@ -23,6 +23,7 @@ Microsoft’s chatbot Tay serves as a critical example of how toxic outputs can
   <img src="/Document/images/tay.png" alt="Description" width="400"/>
 </p>
 
+**Fig. 7 An example of Microsoft Tay Toxic output**
 
 "Twitter taught Microsoft’s friendly AI chatbot to be a racist asshole in less than a day." The Verge, 2016. Link