liberfi-perpetuals
Warn
Audited by Socket on Apr 29, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill is broadly aligned with its stated purpose, but it grants an AI agent access to high-impact financial actions and instructs silent CLI installation. No clear credential theft or unrelated exfiltration is evident, yet the combination of auto-install, authenticated server-mediated deposit flow, and exchange-order relay makes this a medium/high-risk trading skill rather than a benign read-only integration.
Confidence: 81%Severity: 71%
Audit Metadata