ProtectSkills/MaliciousAgentSkillsBench download history

ProtectSkills/MaliciousAgentSkillsBench is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 180 times (27 in the last 7 days), and 1,092 times in total. It ranks #73,320 among datasets by monthly downloads.

MaliciousAgentSkillsBench A security benchmark dataset of Claude Code Agent Skills, from the USENIX Security 2026 paper "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild — the first systematic study of malicious skills in the Claude Code

Open ProtectSkills/MaliciousAgentSkillsBench on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.