ClawHub
Back to skill

Security audit

Edge TTS — Text-to-Speech

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Edge TTS helper, but users should treat submitted text as data sent to Microsoft's online TTS service.

Install is reasonable for ordinary text-to-speech tasks. Do not use it for secrets, credentials, private documents, regulated data, or confidential transcripts unless you are comfortable with Microsoft processing that text. Review optional README commands before running them, especially those that download models or use trust_remote_code.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation advertises reading input from a file and writing audio output to an arbitrary path, but it does not declare corresponding permissions. That mismatch can bypass user expectations and platform governance around filesystem access, increasing the chance of unintended data exposure or overwriting files when the skill is invoked.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The README promotes Edge TTS as 'free' and '无需 API Key' but does not clearly disclose that synthesis is performed by a remote Microsoft service, meaning user-supplied text leaves the local environment. In an agent skill context, prompts, transcripts, names, or other sensitive content may be sent to a third party without the operator realizing it, creating privacy, compliance, and data-handling risk.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill sends user-provided text to Microsoft's Edge TTS service over the network, but the description does not clearly warn users that their content leaves the local environment. This can lead to accidental disclosure of sensitive text, secrets, or proprietary content, especially because the skill is framed as 'free' and 'no API key needed,' which may make it feel more local or lower-risk than it is.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.