Author

Gelei Deng

h-index 25 View on Semantic Scholar

We have 1 of 69 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection

The results show that reliable malicious-Skill detection requires both broader cross-source benchmark coverage and evaluation that jointly measures attack detection and benign over-flagging.

Yue Wang, Yi Liu, Gelei Deng et al. · 0 citations