nano-banana-2
Warn
Audited by Socket on Apr 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's image-generation purpose is coherent, but it hinges on installing and trusting an external `infsh` binary via pipe-to-shell, then logging into that CLI and routing prompts/images through inference.sh rather than direct Google endpoints. Same-org documentation lowers deception concerns, but the unverifiable CLI + credential forwarding combination forces high security risk.
Confidence: 86%Severity: 82%
Audit Metadata