cosyvoice-speech-synthesizer

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward cloud text-to-speech skill that uses the user's DashScope API key to send requested text to Alibaba Cloud and save the returned audio file.

Install only if you are comfortable using an Alibaba Cloud DashScope API key and sending the text you synthesize to that service. Avoid submitting secrets, private messages, regulated data, or confidential business text unless the provider's data terms are acceptable, and use a dedicated/scoped key where possible.

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
88% confidence
Finding
The invocation examples use broad, ordinary-language phrases such as requests to 'synthesize' arbitrary text, which can overlap with normal conversation. In agent environments, that increases the risk of accidental skill activation and unintended transmission of user text to the external TTS provider.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The documentation says the tool can infer intent from free-form natural language like dialect, emotion, or role instructions, without clear activation boundaries. That ambiguity broadens the matching surface and can cause the skill to process text the user did not intend to send to a third party.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill asks users to provide text for synthesis and configure a cloud API key, but it does not clearly warn that submitted text will be sent to a third-party service and may contain sensitive information. Users may unknowingly expose personal, confidential, or regulated data through the synthesis request.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal