SkillGate screens skill files before install at F1=0.817 with 77% fewer LLM tokens.

arXiv 2607.25619 uses a regex prefilter that lets safe Markdown skill packages bypass the LLM judge entirely, sending only matched snippet windows for flagged files. On SkillsBench (n=1,650, 9.1% malicious) it hits 1.13% FPR and beats two existing tools by 5-6x on AUPRC. The threat is independently confirmed: Snyk's February audit of 3,984 ClawHub and skills.sh skills found 534 with a critical issue and 76 confirmed malicious payloads, 8 still live at publication.