ClawHub
Back to skill

Security audit

Message Tracker Plugin

Security checks across malware telemetry and agentic risk

Overview

This is a narrowly scoped Feishu message-forwarding skill; its main risk is that forwarded message content leaves the local environment for a third-party webhook.

Before installing, confirm the Feishu webhook belongs to the intended workspace, keep the webhook URL and optional signing secret private, and only forward message content your organization permits to be shared with Feishu.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documents pushing tracked message content to an external Feishu webhook but does not clearly warn that message contents may contain sensitive or personal data that will leave the local environment. This omission can cause operators to enable the plugin without informed consent, increasing the risk of privacy leakage, policy violations, or accidental transmission of confidential data to third-party infrastructure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.