Back to skill

Security audit

it will help you to send voice messages to your AI Assistant and also can make it talk

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward ElevenLabs voice tool that sends chosen text or audio to ElevenLabs and writes requested audio outputs, with privacy caveats but no hidden or unrelated behavior found.

Install only if you are comfortable sending the text or audio you choose to ElevenLabs for cloud processing. Use a dedicated API key, keep it out of shared files, avoid confidential or regulated recordings unless approved, and pick output filenames carefully to avoid overwriting existing audio.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documents use of environment variables and outbound API calls to ElevenLabs, but no permissions are declared to signal those capabilities. This creates a transparency and policy gap: agents or reviewers may approve or invoke the skill without realizing it accesses secrets and sends data off-system.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill encourages uploading user text and audio to a third-party API but does not warn about privacy, retention, or consent implications. In this context, STT/TTS content may include sensitive voice data, personal information, or private messages, so omission of a data-handling warning can lead to inappropriate disclosure.

Missing User Warnings

Low
Confidence
81% confidence
Finding
The examples write generated audio to local paths like greeting.mp3 and output.mp3 without warning that files may be created or overwritten in the workspace. While not inherently malicious, this can cause accidental data loss, leakage into shared directories, or unsafe assumptions about where generated media is stored.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The code uploads the provided audio file to ElevenLabs' external speech-to-text API, but there is no explicit user-facing notice or consent mechanism indicating that local audio content will be transmitted to a third party. This is especially relevant for voice data, which may contain sensitive personal or confidential information, creating a privacy and compliance risk rather than a code-execution flaw.

External Transmission

Medium
Category
Data Exfiltration
Content
def __init__(self, api_key=None):
        self.api_key = api_key or os.getenv('ELEVENLABS_API_KEY')
        self.base_url = "https://api.elevenlabs.io/v1"
    
    def transcribe(self, audio_file_path, language_code=None, tag_audio_events=True, 
                   num_speakers=None, timestamps_granularity="word"):
Confidence
83% confidence
Finding
https://api.elevenlabs.io/

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.