voice-agents

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a workflow that ingests untrusted external data which could influence agent behavior.
  • Ingestion points: User audio is captured via audioStream and transcribed into text using the Deepgram or OpenAI Realtime APIs as seen in SKILL.md.
  • Boundary markers: The transcribed text (userText) is interpolated directly into the LLM messages array ({ role: 'user', content: userText }) without the use of specific delimiters or system instructions to ignore potential commands embedded in the speech.
  • Capability inventory: The skill has the capability to perform network requests to external AI services (OpenAI, Deepgram, ElevenLabs) and control local audio output devices.
  • Sanitization: There is no evidence of text sanitization, filtering, or validation performed on the transcription before it is passed to the language model for response generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 05:42 PM
Security Audit — agent-trust-hub — voice-agents