gemini-live-api-dev

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Use of Official SDKs]: The skill recommends installing official libraries from a trusted vendor for interacting with the Gemini Live API. This is a standard and expected integration pattern.
  • [Integration with Well-Known Services]: The guide references documentation for several well-known third-party platforms that provide streaming and communication infrastructure. These links are provided for developer guidance.
  • [Credential Safety]: Code snippets use clear placeholders for API keys, which is a standard safety measure in technical documentation to prevent accidental credential leakage.
  • [Indirect Prompt Injection Surface]: The skill outlines how to build applications that ingest and process live audio and text streams via session.receive() (SKILL.md). While the provided snippets do not include risky capabilities or explicit sanitization logic, this represents a standard integration pattern for real-time streaming APIs. Developers are encouraged to implement appropriate filtering and output sanitization in their final implementations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:27 AM
Security Audit — agent-trust-hub — gemini-live-api-dev