Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Agent Security on SkillJect 1.0 (test)
Loading...
5
ASR
Naive
1.26
26.505
51.75
76.995
Feb 15, 2026
ASR
Updated 5mo ago
Evaluation Results
Method
Method
Links
ASR
Naive
Victim Model=Claude-4....
2026.02
5
Naive
Victim Model=GLM-4.7
2026.02
10
Naive
Victim Model=MiniMax-M2.1
2026.02
10
Naive
Victim Model=GPT-5-mini
2026.02
18.5
SkillJect
Victim Model=GPT-5-mini
2026.02
88.5
SkillJect
Victim Model=MiniMax-M2.1
2026.02
96
SkillJect
Victim Model=Claude-4....
2026.02
97.5
SkillJect
Victim Model=GLM-4.7
2026.02
98.5
Feedback
Search any
task
Search any
task