nano-banana-2
Warn
Audited by Socket on Jul 22, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The model usage itself matches the stated purpose, but the skill’s actual trust chain is not clean: it asks users to install a separate `belt-sh/cli` skill not verified by official inference.sh documentation, then to authenticate and route data through that external CLI. This is mainly a supply-chain and credential-forwarding concern, not confirmed malware.
Confidence: 85%Severity: 78%
Audit Metadata