gemini-nano-banana
Warn
Audited by Socket on Mar 30, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's broad behavior mostly matches image-generation/OCR tooling, but its core data flow is inconsistent with a normal Gemini integration because all access is routed through a third-party gateway using a gateway-specific credential. The install sources look plausibly publisher-linked, so this is not confirmed malware, but credential forwarding and intermediary API routing materially raise risk.
Confidence: 87%Severity: 79%
Audit Metadata