gemini-live-api-dev

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • Official SDK Usage: The skill recommends the official and up-to-date Python (google-genai) and JavaScript (@google/genai) SDKs for Gemini Live API development.
  • Secure Authentication Guidance: It explicitly advises against exposing API keys in client-side environments, recommending the use of ephemeral tokens instead.
  • Trusted Documentation Sources: All primary documentation links and fallback URLs point to official google.dev and google.com subdomains.
  • Input Processing Considerations (Indirect Prompt Injection Surface): This skill demonstrates handling untrusted user data (audio, video, text) via the send_realtime_input methods in SKILL.md (Ingestion Points). No explicit boundary markers or sanitization logic are included in the educational snippets (Boundary Markers and Sanitization absent). The skill's capabilities focus on real-time WebSocket interaction with the Gemini Live API (Capability Inventory). Developers should apply standard LLM input validation when moving to production.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 12:21 AM