sgdk-localization
Warn
Audited by Socket on Oct 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s stated localization/build purpose is coherent, and it does not show obvious credential theft or exfiltration. However, it relies on an unverified third-party Docker image via a mutable latest tag, which triggers high supply-chain risk for an AI agent skill even without other malicious behavior.
Confidence: 83%Severity: 78%
Audit Metadata