ClawHub

小米tts文字转语音

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Xiaomi/MiMo text-to-speech skill, but users should know their text is sent to a remote TTS API.

Install only if you are comfortable sending the text you convert to Xiaomi/MiMo's remote TTS service. Do not use it for secrets, private notes, or confidential prompts unless that sharing is acceptable, and prefer a limited API key.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding
The skill documentation indicates use of both environment variables and outbound network access (`MIMO_API_KEY`, remote TTS API), but no permissions are declared. Undeclared capabilities undermine user/operator awareness and policy enforcement, increasing the risk of silent data egress or misuse of secrets even if the intended function is legitimate TTS synthesis.

Vague Triggers

Medium
Confidence
76% confidence
Finding
The description uses broad, everyday phrases like '发语音', '念给我听', and '说话', which can match normal conversation and cause unintentional invocation. In an agent environment, overly generic triggers can lead to surprise activation and unintended transmission of user text to an external synthesis service.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script sends arbitrary user-provided text to a third-party TTS API, which can expose sensitive or private content if users paste secrets, personal data, or confidential text. In the context of a TTS skill this remote processing is expected, but the lack of an explicit notice or consent mechanism increases the chance of inadvertent data disclosure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal