coloring-page
Warn
Audited by Socket on Sep 22, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated purpose is plausible and the Gemini API key is proportionate, but the skill's real execution depends on an unverifiable local binary and an unspecified transitive skill. That makes install trust and credential forwarding the primary risks even without evidence of outright malicious exfiltration.
Confidence: 86%Severity: 78%
Audit Metadata