gemini-3-pro-imagegen
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill integrates with the official
google-genaiPython SDK to perform image generation and editing tasks. - [SAFE]: No hardcoded API keys or credentials were found; the skill correctly instructs the user to use the
GOOGLE_API_KEYenvironment variable. - [SAFE]: External dependencies (
google-genai,pillow) are standard, well-maintained libraries from trusted sources. - [SAFE]: The included Python script (
scripts/generate_image.py) uses safe practices for argument parsing and file system operations, with no evidence of command injection or dangerous dynamic execution. - [SAFE]: Network communication is restricted to official Google API endpoints (
generativelanguage.googleapis.com) and standard Google Search grounding tools. - [SAFE]: The skill provides explicit guidance to the agent on safe file output practices, specifically forbidding the use of temporary directories like
/tmpto ensure data persistence and visibility.
Audit Metadata