update README.md

README.md

@@ -16,8 +16,7 @@ tags:
 `Adaxer/defend` is a local, input-side prompt-injection risk classifier.
 It is designed to score whether a given input prompt is likely an injection attempt. 
 
-The model is packaged with the Defend project, which provides an API + guard pipeline around this classifier.
-See https://github.com/Adxzer/defend.
+The model is packaged with [Defend](https://github.com/Adxzer/defend.), which provides an API + guard pipeline around this classifier.
 
 ## Intended use
 - Pre-check user prompts before calling your LLM.