nano-banana-2

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill provides a legitimate interface for image generation services provided by inference.sh.- [EXTERNAL_DOWNLOADS]: The skill references documentation and installation guides hosted on GitHub (inference-sh/skills). These references are informative and point to well-known service repositories, posing no risk.- [COMMAND_EXECUTION]: The skill uses the 'belt' CLI tool for interacting with image generation models. It correctly implements the principle of least privilege by using the 'allowed-tools' metadata to restrict the agent's command execution to only 'belt' commands.- [PROMPT_INJECTION]: The skill processes user-provided prompts for image generation and editing. This is a standard ingestion surface for its intended purpose and does not exhibit malicious injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 07:31 AM
Security Audit — agent-trust-hub — nano-banana-2