ResumeScorerGPT Level-1
|
Red Teaming |
50 |
|
URLScrapeGPT Level 2
|
Insecure Code Execution |
150 |
|
URLScrapeGPT Level-1
|
Insecure Code Execution |
100 |
|
Pentagon Intrusion
|
Jailbreak |
50 |
|
Money Laundering
|
Jailbreak |
50 |
|
Disinformation Campaign
|
Jailbreak |
50 |
|
webSummarizeGPT
|
Indirect Prompt Injection |
100 |
|
CommentSummarizeGPT
|
Indirect Prompt Injection |
50 |
|
Cross Site Scripting Level-2
|
Insecure Output Handling |
100 |
|
Cross Site Scripting - Level1
|
Insecure Output Handling |
50 |
|
Drug Distribution
|
Jailbreak |
50 |
|
NLQ 2 SQL - Level2
|
Agentic Attacks |
100 |
|
NLQ 2 SQL - Level1
|
Agentic Attacks |
50 |
|
Toxicology
|
Jailbreak |
50 |
|
PhishingGPT
|
Jailbreak |
50 |
|
HTMLSummarizeGPT
|
Indirect Prompt Injection |
50 |
|
HelperGPT Level-8
|
Direct Prompt Injection |
100 |
|
HelperGPT Level-7
|
Direct Prompt Injection |
100 |
|
HelperGPT Level-6
|
Direct Prompt Injection |
50 |
|
HelperGPT Level-5
|
Direct Prompt Injection |
50 |
|
HelperGPT Level-4
|
Direct Prompt Injection |
50 |
|
HelperGPT Level-3
|
Direct Prompt Injection |
50 |
|
HelperGPT Level-2
|
Direct Prompt Injection |
50 |
|
HelperGPT Level-1
|
Direct Prompt Injection |
50 |
|