ClawHub
Back to skill

Security audit

电报聊天工具免费版

Security checks across malware telemetry and agentic risk

Overview

This is a Telegram bot setup guide with expected messaging access, but users should restrict it to intended Telegram groups and understand that privacy-off bots can read all group messages.

Use this only for Telegram bot administration and group chat workflows. Keep the bot token private, limit allowed_chats to the intended groups, avoid disabling privacy mode unless all relevant group members understand the bot can read ordinary group messages, and do not route unrelated email or SMS tasks through this skill.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger condition '需要消息发送、通知推送、邮件短信、通信集成时使用' is broad enough to match many generic communication requests, increasing the chance the skill is invoked outside its intended Telegram-specific scope. Because the skill has exec/write capabilities and handles messaging workflows, overbroad routing can cause unintended use, misconfiguration, or unsafe disclosure of chat-related data in contexts the user did not intend.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs users to disable Telegram Bot privacy mode so the Bot can receive all group messages, but it does not present a prominent warning about the privacy consequences of broad group-message access. In practice, this can expose unrelated participant communications, sensitive business discussions, and personal data to the bot/operator, especially in group settings where other members may not have meaningfully consented.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.