ClawHub
Back to skill

Security audit

Devin_dingcheng

Security checks across malware telemetry and agentic risk

Overview

This skill appears to query an IoT liquid-level sensor as advertised, but it asks users to send an API key, phone number, and device identifier to an external service without enough privacy or trust guidance.

Install only if you trust the cd6969.com service and are comfortable sending it the API key, phone number, and device identifier. Use a least-privilege key if available, avoid pasting real secrets into shell history, and confirm the endpoint is the correct provider API before using it with real devices.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
76% confidence
Finding
The skill documents shell-based execution (`curl` and `./scripts/get_status.sh`) but does not declare corresponding permissions or execution capabilities. This creates a transparency and policy gap: users or platforms may not realize the skill can invoke shell commands and access the network, which increases the chance of unintended execution and weakens review controls.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The documentation instructs users to send sensitive identifiers (`key`, `tel`, and elsewhere `imei`) to a third-party remote API without any privacy notice, data-handling explanation, or consent guidance. These values can uniquely identify the user and device, and exposing them to an external service without disclosure creates privacy, tracking, and credential-misuse risk.

External Transmission

Medium
Category
Data Exfiltration
Content
## 快速查询

```bash
curl -s -X POST "https://www.cd6969.com/admin.php?s=/Admin/ApiV2/getList.html" \
  -H "Content-Type: application/json" \
  -d '{"key":"你的KEY","tel":"你的手机号"}'
```
Confidence
91% confidence
Finding
curl -s -X POST "https://www.cd6969.com/admin.php?s=/Admin/ApiV2/getList.html" \ -H "Content-Type: application/json" \ -d

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.