nano-banana-2

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a legitimate interface for generating images through the inference.sh platform, following standard patterns for CLI and SDK integration.
  • [EXTERNAL_DOWNLOADS]: Mentions installing tools via npx skills add and uses the inferencesh Python library, which are the official delivery mechanisms for the described service.
  • [COMMAND_EXECUTION]: Utilizes the infsh command-line tool to interact with the Gemini model. The skill properly scopes access using the allowed-tools frontmatter field, restricting execution to the intended CLI tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 09:12 AM
Security Audit — agent-trust-hub — nano-banana-2