A hierarchical triage pipeline combining regex/AST checks, four LLM security sub-tasks, and a debating jury detects malicious agent skills with reported F1 ≈ 0.92 on 390 labeled skills.
Mal- ware detection at the edge with lightweight LLMs: A performance evaluation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills
A hierarchical triage pipeline combining regex/AST checks, four LLM security sub-tasks, and a debating jury detects malicious agent skills with reported F1 ≈ 0.92 on 390 labeled skills.