nano-banana

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to run the infsh command-line tool to interact with Google Gemini image models. This tool access is explicitly defined and limited in the skill metadata.- [EXTERNAL_DOWNLOADS]: The documentation provides links to install the infsh CLI from the author's official GitHub repository and suggests adding related skills using the npx skills command. These are standard deployment methods for the vendor's platform.- [SAFE]: Analysis of the skill instructions and examples reveals no malicious intent, prompt injection, or unauthorized data access. The behavior is consistent with the stated purpose of providing an interface for Gemini-based image generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:58 PM
Security Audit — agent-trust-hub — nano-banana