gemini-live-api-dev

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official Google documentation hosted at ai.google.dev and recommends installing well-known SDKs (google-genai and @google/genai) from standard package registries.
  • [CREDENTIALS_UNSAFE]: The documentation correctly uses placeholders like 'YOUR_API_KEY' for authentication instead of hardcoding sensitive information.
  • [DATA_EXFILTRATION]: While the skill describes building real-time applications that transmit audio, video, and text data, all communications are directed to official Google API endpoints as part of the intended functionality of the Gemini Live API.
  • [COMMAND_EXECUTION]: No shell commands or direct system executions are present in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 12:52 PM
Security Audit — agent-trust-hub — gemini-live-api-dev