Lucene search
+L

1 matches found

Kitploit
Kitploit
•added 2026/10/27 1:12 a.m.•11 views

guardrebind

Fooling LLM Safety Guards into Judging the Wrong Text Code, data and every raw score for the paper paper/main.pdf, source in paper/. LLM safety guards receive the content they review by plain string interpolation into their grading prompt, so content that imitates the guard's own prompt format ca...

6.2AI score
SaveExploits0
Rows per page
Query Builder