cure
Warn
Audited by Socket on Oct 19, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s remediation workflow is mostly aligned with its purpose, but it relies on an opaque bundled .pyz executable and can autonomously hand off to publication via /plate despite claiming not to be for direct publication. I found no clear credential harvesting or exfiltration, so this is higher security risk from execution trust and autonomous workflow impact rather than confirmed malware.
Confidence: 82%Severity: 72%
Audit Metadata