ClawHub
Back to skill

Security audit

MiniMax TTS 国内版

Security checks across malware telemetry and agentic risk

Overview

This is a normal MiniMax text-to-speech skill that sends user-provided text to MiniMax and saves returned audio locally.

Install only if you are comfortable sending the text you ask it to speak to MiniMax. Avoid using it for secrets, private messages, regulated data, or confidential drafts unless your MiniMax account and data-handling terms are acceptable.

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 (1)

External Transmission

Medium
Category
Data Exfiltration
Content
try:
        print(f"正在生成语音...", file=sys.stderr)
        resp = requests.post(url, headers=headers, json=data, timeout=60)
        resp.raise_for_status()
        result = resp.json()
Confidence
88% confidence
Finding
The function sends arbitrary user-provided text and an API credential to a third-party TTS endpoint. In a skill context, this can expose sensitive prompts or user data to an external provider if callers pass secrets, and the script provides no consent notice, redaction, or data-classification guardrails.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.