vox-best-practice

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of documentation and reference materials for vox.ai development. No malicious code or obfuscation was found.
  • [EXTERNAL_DOWNLOADS]: The skill references the official vox.ai MCP server URL (https://mcp.tryvox.co/). This is a trusted vendor resource for legitimate integration.
  • [CREDENTIALS_UNSAFE]: Security-sensitive information like API keys is handled using placeholders and environment variable instructions, preventing credential leakage.
  • [COMMAND_EXECUTION]: Shell command examples are provided for user configuration of AI clients and do not represent unauthorized command execution by the agent.
  • [PROMPT_INJECTION]: The skill includes instructions to prevent hallucinations and meta-talk in voice agents, improving reliability without attempting to bypass safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 12:59 AM