nano-banana
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
infsh(Inference Shell) CLI to perform login, list applications, and execute image generation tasks. These commands are localized to the vendor's toolset and do not involve sensitive system parameters. - [EXTERNAL_DOWNLOADS]: The skill documentation references external sources for installation (
npx skills add) and documentation (inference.sh). These sources are consistent with the skill author 'inference-shell' and represent standard vendor-provided resources. - [PROMPT_INJECTION]: No prompt injection markers, role-play instructions, or safety bypass attempts were detected in the skill instructions or metadata.
- [DATA_EXFILTRATION]: No patterns of sensitive data access or exfiltration to unauthorized domains were found. The network operations are directed towards the vendor's own API via their CLI tool.
Audit Metadata