List your company

Malicious AI Agent Skill Detection on 400 labeled skills (89 malicious, 311 benign)

100PrecisionSkillSieve L1 + Single prompt
30.21648.33366.4584.567Apr 8, 2026

Evaluation results

MethodLinks
SkillSieve L1 + Single promptLayer 1=L1 triage, Layer 2=Single prompt2026.0410059.674.6910
SkillSieve L1 + SSDLayer 1=L1 triage, Layer 2=Structured Semantic Decomposition (SSD)2026.0475.285.48090.58
SkillSieve L1Layer=L1 triage2026.0458.398.973.38420.3
ClawVet2026.0432.958.442.164.234.1