智能配音合成虾

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.0.0

Overview

The skill is a mostly coherent voice-synthesis tool, but it unnecessarily instructs agents to print API keys, which could expose paid service credentials.

Review before installing. Do not run the documented API-key echo command; use presence-only checks for credentials. Only use this with text you are comfortable sending to ElevenLabs or OpenAI, and expect generated audio files to be written locally.

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

High

• Confidence: 98% confidence
• Finding: The skill explicitly tells the agent to run a shell command that echoes API key environment variables, which can expose secrets in logs, chat transcripts, or to the user. In a skill context, instructing secret material to be printed is a direct confidentiality risk and is more dangerous because the values include credentials for external services.

VirusTotal

67/67 vendors flagged this skill as clean.