skills/usevowel/skills/vowel-vanilla/Gen Agent Trust Hub

vowel-vanilla

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the @vowel.to/client library and the @ricky0123/vad-web package for voice activity detection. These are standard, expected dependencies for the skill's stated purpose of integrating voice agents.
  • [PROMPT_INJECTION]: The skill describes a 'Sub-Agent' pattern where the voice agent can delegate tasks to other in-app AI interfaces via custom actions. While this establishes a channel for processing data from multiple LLMs, it is a documented architectural feature for orchestrating complex application workflows and does not contain malicious injection attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 02:06 PM