ClawHub
Back to skill

Security audit

MOSS Voice Generator 指令式音色生成

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward cloud voice-generation skill that sends requested text and style prompts to MOSI Studio and saves the returned audio file.

Install this only if you trust MOSI Studio to process the text you synthesize. Avoid sending confidential, personal, or regulated content unless MOSI’s handling terms are acceptable, and prefer using MOSI_TTS_API_KEY from the environment instead of passing the key on the command line.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script transmits user-supplied text and voice-style instructions to a third-party cloud API, but it does not clearly disclose this data egress at runtime or require explicit user confirmation. This can expose sensitive or confidential content if callers assume the synthesis happens locally, especially in an agent context where arbitrary user prompts may be forwarded automatically.

External Transmission

Medium
Category
Data Exfiltration
Content
echo "Generating voice..." >&2

RESPONSE=$(curl -sf -X POST \
  "https://studio.mosi.cn/api/v1/audio/speech" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
Confidence
89% confidence
Finding
curl -sf -X POST \ "https://studio.mosi.cn/api/v1/audio/speech" \ -H "Authorization: Bearer $API_KEY" \ -H "Content-Type: application/json" \ -d

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal