Elevenlabs

• Outcome: Pass
• Latest audit: May 28, 2026, 4:48 AM
• Version:
  1.3.4

Overview

This skill is a coherent ElevenLabs audio helper, but users should treat the API key and voice-cloning samples as sensitive.

Install only if you are comfortable using your ElevenLabs API key from this environment. Store the key securely, avoid committing .env files, and only use voice-cloning samples that you are authorized to upload and clone.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill metadata declares runtime requirements and the documentation clearly describes capabilities including environment-variable access, file reads/writes, network API calls, and shell execution, yet no explicit permissions model is declared. This creates a transparency and governance gap: users or orchestrators may under-scope the skill's access, increasing the chance of unintended secret exposure, filesystem access, or command execution during use.

Missing User Warnings

Low

• Confidence: 91% confidence
• Finding: The setup documentation explicitly allows storing the ElevenLabs API key in a `.env` file on disk but does not warn users that this creates a persistent credential file that can be exposed through weak file permissions, backups, accidental commits, or local compromise. While common in developer workflows, documenting disk-based secret storage without protective guidance increases the chance of credential leakage.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill exposes voice cloning functionality but provides no warning or safeguards around consent, impersonation risk, biometric/privacy sensitivity, or lawful use of voice samples. In this context, the omission materially increases the chance of misuse for unauthorized cloning, social engineering, fraud, or privacy violations, especially because the feature is directly operationalized with simple commands.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: This script uploads local audio samples to a third-party API to create a voice clone, but it does not present an explicit runtime warning or consent check about transmitting biometric voice data off-device. In the context of voice cloning, the privacy implications are significant because users may upload sensitive or non-consensual recordings without a clear notice.

VirusTotal

66/66 vendors flagged this skill as clean.