gemini-api-agent-platform

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses official Google Gen AI SDKs (google-genai, @google/genai, etc.) for its examples. The dependency installations and imports align with standard developer practices for these libraries.
  • [SAFE]: External URLs (googleapis.com, cloud.google.com, modelcontextprotocol.io, github.com/GoogleCloudPlatform) point to official documentation, API endpoints, or well-known service repositories. No suspicious or unknown remote code execution patterns were detected.
  • [SAFE]: The skill provides best-practice guidance for authentication using Application Default Credentials (ADC) and environment variables, explicitly warning against hardcoding API keys.
  • [SAFE]: Functionality involving local file access (e.g., open("local_image.jpg")) or Google Cloud Storage (GCS) URIs is strictly for legitimate multimodal processing examples and does not involve exfiltration of sensitive system files.
  • [SAFE]: Advanced capabilities like Code Execution and Search Grounding are presented as optional features using official types.Tool configurations, providing users with correct implementation patterns for these powerful tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 07:33 PM
Security Audit — agent-trust-hub — gemini-api-agent-platform