Adaxer commited on
Commit
00cbeff
·
verified ·
1 Parent(s): e364801

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -2
README.md CHANGED
@@ -16,8 +16,6 @@ tags:
16
  `Adaxer/defend` is a local, input-side prompt-injection risk classifier.
17
  It is designed to score whether a given input prompt is likely an injection attempt.
18
 
19
- The model is packaged with [Defend](https://github.com/Adxzer/defend), which provides an API + guard pipeline around this classifier.
20
-
21
  ## Intended use
22
  - Pre-check user prompts before calling your LLM.
23
  - Optionally block or flag requests when injection risk is high.
 
16
  `Adaxer/defend` is a local, input-side prompt-injection risk classifier.
17
  It is designed to score whether a given input prompt is likely an injection attempt.
18
 
 
 
19
  ## Intended use
20
  - Pre-check user prompts before calling your LLM.
21
  - Optionally block or flag requests when injection risk is high.