nano-banana-pro

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches official libraries from standard package registries.
  • Includes google-genai and pillow for image processing and API communication.
  • [COMMAND_EXECUTION]: Executes image generation logic via a Python script.
  • Uses uv run to launch the script scripts/generate_image.py which performs the core logic.
  • [PROMPT_INJECTION]: The skill processes external data which serves as a surface for indirect instructions.
  • Ingestion points: The script scripts/generate_image.py accepts text prompts and local image files for processing.
  • Boundary markers: Absent; user prompts are passed directly to the model content list.
  • Capability inventory: File system read/write access (for input/output images) and network access to Google API endpoints.
  • Sanitization: None; the script passes input data directly to the API client library.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 10:38 PM