create-worktree
Warn
Audited by Socket on May 12, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated purpose is coherent, and HumanLayer appears to be a legitimate same-org tool with official docs and source, but the skill depends on executing unverifiable local scripts and can trigger a chained implementation/commit/PR workflow after a single confirmation. Risk is driven more by local script trust and autonomous side effects than by clear malicious intent.
Confidence: 83%Severity: 72%
Audit Metadata