nano-banana

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a restricted tool scope for Bash(infsh *), which prevents the agent from executing arbitrary shell commands outside the intended CLI utility.
  • [EXTERNAL_DOWNLOADS]: The skill references legitimate assets and documentation from inference.sh. These are categorized as safe as they originate from the primary service provider.
  • [REMOTE_CODE_EXECUTION]: No automatic remote code execution was detected. The provided installation commands for the infsh CLI and related skills are standard developer setup instructions.
  • [DATA_EXFILTRATION]: No patterns indicative of credential harvesting or data exfiltration were found. Access to external URLs is limited to common image processing tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 09:12 AM
Security Audit — agent-trust-hub — nano-banana