ClawHub

WeCom Bot

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a disclosed WeCom message-sending connector, but its routing claims and install guidance are broader and riskier than the actual five send actions justify.

Install only if you intend to use OOMOL's oo CLI and server-side WeCom Bot connection to send messages. Review the installer source or use a safer verified install path before running the setup commands, and require explicit confirmation of message payloads before any send action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The instruction to use this skill for ANY WeCom Bot request is overly broad relative to the actual functionality, which only supports outbound message sending. In an agentic environment, such broad routing language can cause the skill to be invoked for unrelated WeCom tasks, leading to unintended message posting, incorrect task handling, or bypass of more appropriate tools and confirmation logic.

External Script Fetching

High
Category
Supply Chain
Content
- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):

  ```bash
  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  ```

  ```powershell
Confidence
97% confidence
Finding
curl -fsSL https://cli.oomol.com/install.sh | bash

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal