ClawHub
Back to skill

Security audit

feishu-edge-tts-win

Security checks across malware telemetry and agentic risk

Overview

This skill openly converts user-provided text to speech and sends it as a Feishu voice message, with expected use of Feishu credentials and external services.

Install only if you are comfortable with the message text and generated audio leaving your machine for Edge TTS and Feishu processing. Protect the OpenClaw config file, use least-privilege Feishu app credentials, verify the recipient open_id before running the command, and avoid sending secrets or regulated data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill documentation clearly instructs use of file access, shell execution, and outbound network access, but no declared permissions are shown. That mismatch is dangerous because users and hosting frameworks cannot accurately understand or constrain the skill's capabilities, increasing the risk of unintended data access, command execution, or external transmission.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation says generated audio is uploaded to Feishu and that credentials are read from a local config file, but it does not prominently warn users that message content and derived audio will leave the local machine. This can lead to unintentional disclosure of sensitive text, misuse of stored app credentials, and poor informed consent around third-party transmission.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.