Update README.md
Browse files
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.
|