Zyt tts voice clone

• Outcome: Pass
• Latest audit: May 29, 2026, 8:30 PM
• Version:
  0.4.0

Overview

This is a Chanjing voice-clone text-to-speech skill that uses the expected external API and local Chanjing credentials, with no evidence of hidden or unrelated behavior.

Install only if you are comfortable sending the reference voice URL and synthesis text to Chanjing. Use voice samples you have permission to clone, avoid confidential text, store Chanjing credentials with restrictive permissions, and rotate the key if you stop using the skill.

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 (2)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill sends user-provided reference voice audio URLs and speech generation text to a third-party TTS provider, but the description lacks an explicit warning to the user. This is dangerous because voice samples and generated content may be sensitive personal or proprietary data, and users may unknowingly disclose them to an external service.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explains that it reads local API credentials from ~/.chanjing/credentials.json or a configurable directory, but it does not clearly warn the user that local secrets will be accessed and used for authentication. Hidden credential usage is risky because it reduces informed consent and can surprise users who did not expect local secret material to be consumed by the skill.

VirusTotal

57/57 vendors flagged this skill as clean.