nano-banana-pro

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides image generation and editing capabilities using the official Google Gemini API (google-genai) and the Pillow (PIL) library for image processing.
  • [EXTERNAL_DOWNLOADS]: The skill correctly identifies dependencies in its script header (google-genai and pillow). These are well-known, standard libraries from official registries (PyPI).
  • [CREDENTIALS_UNSAFE]: The skill uses the 'GEMINI_API_KEY' environment variable for authentication, which is the standard and secure practice for this type of tool. It does not contain any hardcoded secrets.
  • [COMMAND_EXECUTION]: The script uses 'uv run' to execute its internal Python script. This is a standard and safe method for running local scripts within a managed environment.
  • [DATA_EXFILTRATION]: Network operations are restricted to the official Google Gemini API endpoints for image generation and processing. No unauthorized data exfiltration patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:18 AM