Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Malicious Skill Detection on MaliciousAgentSkillsBench (404 malicious, 502 benign)

100Recall

BIV

32.449.9567.585.05May 12, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
1009999
2026.05
989295
2026.05
939996
2026.05
899793
2026.05
865769
2026.05
647468
2026.05
458860
2026.05
392026
2026.05
356244