Volcengine Ai Audio Tts

• Outcome: Pass
• Latest audit: May 28, 2026, 11:42 AM
• Version:
  1.0.0

Overview

This is a small instruction-only Volcengine text-to-speech skill with no code, installer, persistence, or hidden behavior found.

Install if you are comfortable sending text to Volcengine for speech synthesis. Avoid confidential or regulated text unless your Volcengine account terms and privacy requirements allow that use.

SkillSpector

By NVIDIA

Vulnerability Patterns

• System Prompt Leakage: Direct Leakage, Indirect Extraction, Tool-Based Exfiltration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Direct Prompt Extraction

High

• Category: System Prompt Leakage

Content

3. Execute TTS request and poll if async.
4. Return audio URL/path and reproducible parameters.

## Output Rules

- Prefer stable audio formats (`mp3` or `wav`).
- Keep text chunks short for long passages.

• Confidence: 85% confidence
• Finding: Output Rules

VirusTotal

63/63 vendors flagged this skill as clean.