ClawHub
Back to skill

Security audit

麦当劳MCP自动化工具

Security checks across malware telemetry and agentic risk

Overview

This skill automates real McDonald's account actions using a captured account token, but it does not give enough safety guidance or confirmation boundaries for credentials, coupons, orders, or scheduled use.

Review carefully before installing. Only use it if you understand that MCD_TOKEN can act on your McDonald's account. Avoid putting the token in shell history, scripts, screenshots, shared terminals, or cron entries, and require a manual review of store, items, coupons, price, and final charge before any order-related action.

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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill prominently offers automatic coupon redemption and one-click order placement against a real user account, yet provides no warning that these actions can consume benefits, create orders, or trigger real purchases. In an automation context, missing consent and side-effect warnings materially increase the risk of accidental financial/account actions.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation instructs users to capture and export `MCD_TOKEN` from app traffic without warning that it is a sensitive bearer credential. Anyone who obtains this token may be able to access account functions such as coupons, order operations, and account-linked data, making leakage through shell history, logs, screenshots, or shared environments particularly dangerous.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.