skills/deepgram/skills/voice-agent/Gen Agent Trust Hub

voice-agent

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: As an orchestration guide for voice agents, this skill describes an architecture that ingests untrusted user audio and text, which is an inherent attack surface for indirect prompt injection.
  • Ingestion points: User audio streams and typed messages received via the wss://agent.deepgram.com/v1/agent/converse WebSocket as described in SKILL.md.
  • Boundary markers: The skill mentions the use of agent.think.prompt for system instructions, but does not provide specific guidance on sanitizing or delimiting transcription data before it is processed by the underlying LLM.
  • Capability inventory: The documented architecture supports FunctionCallRequest for client-side tool execution, binary audio generation (TTS), and mid-call updates to the prompt or model configuration.
  • Sanitization: Not explicitly detailed in the protocol reference; implementations rely on the safety guardrails of the chosen LLM provider (OpenAI, Anthropic, etc.).
  • [EXTERNAL_DOWNLOADS]: The skill references official Deepgram repositories and SDKs for implementation and boilerplate code.
  • Evidence: References official examples at github.com/deepgram/examples, github.com/deepgram/recipes, and github.com/deepgram-starters.
  • Evidence: Lists official NPM packages including @deepgram/agents, @deepgram/react, @deepgram/ui, and @deepgram/agents-widget.
  • Evidence: Mentions official SDK skills such as deepgram-js-voice-agent, deepgram-python-voice-agent, and deepgram-go-voice-agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 05:11 PM