ClawHub

mcd-cn

Security checks across malware telemetry and agentic risk

Overview

This McDonald's helper is coherent and disclosed, but users should protect the token and confirm before claiming coupons.

Install only if you trust mcp.mcd.cn and any MCD_MCP_URL value you configure. Keep MCD_TOKEN private, avoid pasting it into logs or public chats, and ask the agent to list available coupons and get clear confirmation before using one-click coupon claiming.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The coupon-claiming triggers are broad and map directly to a state-changing action ('auto-bind-coupons'). In an agent setting, ambiguous phrases like '帮我领券' or '全部领取' can cause unintended account actions without sufficient confirmation or scope checks, especially if invoked from loosely related conversation context.

Vague Triggers

Medium
Confidence
84% confidence
Finding
Generic nutrition triggers like '热量', '卡路里', or '多少大卡' are overly broad and may invoke the McDonald's skill for unrelated food, fitness, or health questions. This can lead to incorrect tool usage, accidental data retrieval, or confusing responses, though the security impact is limited because the action is read-only.

External Transmission

Medium
Category
Data Exfiltration
Content
## 调用方式

使用 exec 工具执行 curl 命令调用 MCP 服务：

```bash
MCD_URL="${MCD_MCP_URL:-https://mcp.mcd.cn}"
Confidence
91% confidence
Finding
curl 命令调用 MCP 服务： ```bash MCD_URL="${MCD_MCP_URL:-https://mcp.mcd.cn}" MCD_AUTH="Authorization: Bearer ${MCD_TOKEN:-<YOUR_TOKEN>}" curl -s -X POST "$MCD_URL" \ -H "$MCD_AUTH" \ -H "Content-Type:

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal