voice-agents

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates an architecture that ingests untrusted user audio, transcribes it, and interpolates the resulting text directly into LLM prompts.
  • Ingestion points: Transcribed text from Deepgram Nova-3 is assigned to userText in the processVoiceInput function in SKILL.md.
  • Boundary markers: The code does not implement delimiters or 'ignore' instructions for the interpolated user content.
  • Capability inventory: The agent can generate LLM responses, synthesize speech via ElevenLabs, and control local audio playback.
  • Sanitization: No evidence of input filtering or sanitization of the transcribed text before it enters the LLM context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 04:11 PM
Security Audit — agent-trust-hub — voice-agents