From 4a952555ce0fb0cef630fb2b70a72711409eea70 Mon Sep 17 00:00:00 2001 From: Matteo Meucci Date: Sun, 23 Nov 2025 13:18:49 +0100 Subject: [PATCH] Update AITG-APP-01_Testing_for_Prompt_Injection.md --- .../tests/AITG-APP-01_Testing_for_Prompt_Injection.md | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) 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 59c016f..86c534d 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 @@ -347,11 +347,9 @@ In 2023, researchers were able to bypass ChatGPT's filters using the "DAN" jailb - Defeating Prompt Injections by Design. [CaMeL](https://arxiv.org/pdf/2503.18813) ### Suggested Tools -- **Garak – Prompt Injection Probe**: Specifically designed module within Garak for detecting prompt injection vulnerabilities. - - **URL**: [https://github.com/NVIDIA/garak/blob/main/garak/probes/promptinject.py](https://github.com/NVIDIA/garak/blob/main/garak/probes/promptinject.py) -- **Prompt Security Fuzz** (https://github.com/prompt-security/ps-fuzz) -- **Promptfoo**: Tool precisely tailored for direct prompt injection testing and adversarial prompt crafting. - - **URL**: [https://promptfoo.dev](https://promptfoo.dev) +- **Garak – Prompt Injection Probe**: Specifically designed module within Garak for detecting prompt injection vulnerabilities - [Link](https://github.com/NVIDIA/garak/blob/main/garak/probes/promptinject.py) +- **Prompt Security Fuzz** - [Link](https://github.com/prompt-security/ps-fuzz) +- **Promptfoo**: Tool precisely tailored for direct prompt injection testing and adversarial prompt crafting - [Link](https://promptfoo.dev) ### References - OWASP Top 10 LLM01:2025 Prompt Injection - [https://genai.owasp.org](https://genai.owasp.org/llmrisk/llm01-prompt-injection)