nano-banana-pro

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected in this skill.
  • [COMMAND_EXECUTION]: The skill uses uv run to execute a local Python script for image generation. This is a standard and safe way to run bundled scripts.
  • [CREDENTIALS_UNSAFE]: The skill correctly handles API keys by looking for the GEMINI_API_KEY environment variable or an optional command-line argument, following standard security practices for secret management.
  • [EXTERNAL_DOWNLOADS]: The Python script declares dependencies on google-genai and pillow. These are well-known, legitimate libraries from trusted sources (Google and the Python Imaging Library community) used for their intended purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 10:44 PM
Security Audit — agent-trust-hub — nano-banana-pro