Security audit

mar-edge-tts

Security checks across malware telemetry and agentic risk

Overview

This is a coherent text-to-speech skill that uses an API key and sends requested text to an external TTS service.

Install only if you are comfortable providing a SkillBoss API key and sending the text you convert to an external TTS provider. Do not convert secrets, credentials, private messages, or regulated data unless that is acceptable for your use case; protect and rotate the API key if exposed; and clean up generated audio files if they contain sensitive content.

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 (4)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The documentation instructs users to set a live API credential in an environment variable but does not include any warning about keeping the key secret, avoiding hardcoding, or preventing accidental exposure in shell history, screenshots, logs, or committed files. In a skill package that depends on a third-party TTS service, this omission increases the chance of credential leakage and subsequent unauthorized API use or billing abuse.

Vague Triggers

Medium

Confidence: 76% confidence
Finding: The trigger guidance is broad enough that the skill may activate on general requests for spoken output, causing unintended transmission of user-provided content to an external TTS service. In a chat agent context, overbroad invocation can create privacy exposure and surprising behavior, especially if sensitive text is converted and sent off-platform without explicit confirmation.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: Relying on a generic keyword like 'tts' without stronger scope constraints can cause accidental invocation from incidental mentions, quoted text, logs, or unrelated user content. Because activation leads to outbound processing and file generation, mistaken triggering can leak data to a third-party API and create unintended artifacts on disk.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The guide explicitly states that node-edge-tts uses Microsoft Edge's online service and requires an internet connection, but it does not clearly warn that user-provided text will be transmitted to a third-party service. In a TTS skill, users may submit sensitive or private content, so omitting a privacy warning can lead to unintended disclosure of confidential data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.env_credential_access

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: scripts/tts-converter.js:17