Polyphone TTS

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:20 PM UTC
• Version:
  1.0.0

Overview

This skill is a purpose-aligned Chinese text-to-speech helper that sends text to SenseAudio using the user's API key, with no hidden install code or persistence found.

Install only if you are comfortable sending the text you synthesize and the selected cloned voice ID to SenseAudio. Protect the SENSEAUDIO_API_KEY, use only voices you are authorized to use, and avoid submitting sensitive or confidential text unless SenseAudio's terms and data handling are acceptable for your use case.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill instructs the agent to send user text and a cloned voice identifier to an external API using a bearer token, but it does not require explicit user-facing disclosure or consent before transmission. This can lead to unintended sharing of potentially sensitive text content and voice-linked identifiers with a third-party service.

VirusTotal

66/66 vendors flagged this skill as clean.