ai-provider-google-gemini-sdk
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate developer documentation for the official Google Gemini SDK (
@google/genai). - [SAFE]: Proper secret management is emphasized throughout the instructions, specifically advising against hardcoding API keys and instead using environment variables like
GEMINI_API_KEYandGOOGLE_API_KEY. - [SAFE]: Documentation regarding safety filters and the use of
BLOCK_NONEis presented within a technical context for backend data processing. This is a standard API feature and is accompanied by clear warnings about the risks of disabling such filters in user-facing applications. - [SAFE]: References to tools such as 'Code Execution' and 'Google Search' pertain to built-in features of the Google Gemini API that execute within Google's managed environment, posing no risk of unauthorized local command execution.
- [SAFE]: Data processing patterns recommended in the skill include the use of Zod for structured output validation and explicit checks of API
finishReasonfor safety blocks, which align with security best practices for LLM integrations.
Audit Metadata