ClawHub
Back to skill

Security audit

WeCom Bot

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent WeCom Bot connector, but it includes broad WeCom write/delete authority and an untagged dynamic tool escape hatch that is not clearly covered by its confirmation rules.

Install only if you trust OOMOL and intend to let the agent operate your connected WeCom Bot account. Confirm every message, schedule, document, sheet, todo, or deletion payload before execution, and be especially cautious with `call_tool` because the artifact does not clearly restrict it to read-only behavior.

SkillSpector

By NVIDIA
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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The description says to use this skill for ANY WeCom Bot request and instead of calling the API directly, which creates an overly broad routing rule. That can cause an agent to invoke a highly privileged integration for loosely related prompts, increasing the chance of unintended data access or writes, especially because the skill exposes many state-changing and destructive actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.