nano-banana

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the 'belt' CLI tool using Bash to perform image generation and editing tasks. Tool access is correctly scoped to the 'belt' command within the allowed-tools configuration.- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the 'belt' CLI and related skills from official 'inference-sh' sources. These references are used for legitimate setup and documentation purposes.- [SAFE]: Analysis of the skill instructions and metadata revealed no evidence of malicious patterns, such as data exfiltration, persistence mechanisms, or code obfuscation. The skill's functional capabilities match its described purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 07:31 AM
Security Audit — agent-trust-hub — nano-banana