check-vanta
Warn
Audited by Socket on Mar 23, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's purpose is coherent for security remediation, and most endpoints are official, but it grants an agent broad autonomous power: reading raw credential files, modifying many repos, pushing branches, and creating public/remote artifacts without user confirmation. This is high-risk autonomy rather than confirmed malware.
Confidence: 92%Severity: 88%
Audit Metadata