ClawHub
Back to skill

Security audit

Edge TTS English

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward text-to-speech helper that sends user-provided text to Microsoft Edge TTS and returns an MP3, with privacy and output-path cautions but no hidden or destructive behavior.

Install this only if you are comfortable sending the text you ask it to speak to Microsoft Edge TTS through the edge-tts client. Do not use it for passwords, secrets, private messages, or confidential documents, verify the edge-tts binary came from a trusted source, and keep generated files in temporary or intended output locations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger list is broad and spans multiple languages and intents without clear routing boundaries, which can cause the skill to activate when the user did not explicitly request text-to-speech. In an agent environment, overbroad activation can misroute user requests, unexpectedly send content to an external TTS service, and create consent/privacy issues if sensitive text is spoken or transmitted.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The metadata claims multilingual support while the skill is framed as an English-speaking tool and instructs sending spoken output directly to the user, without requiring explicit confirmation of language choice. This can lead to the agent overriding user intent, producing content in an unintended language/accent, and transmitting user text to the TTS backend without clear opt-in for that behavior.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script sends arbitrary user-provided text to the external Microsoft Edge TTS service via the edge-tts client, but there is no warning, consent step, or indication that the text leaves the local environment. This can expose sensitive user content if the skill is used on private, personal, or confidential text under the assumption that processing is local-only.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.