Security audit

Mcdonald - 麦当劳助手

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed McDonald's helper that uses a user-provided token to query and claim coupons through the stated MCP service, with no hidden code or persistence found.

Install only if you trust the McDonald's MCP service and can keep MCD_TOKEN private. Leave MCD_MCP_URL at the default unless you intentionally verified another endpoint, and treat one-click coupon claiming as an account-changing action that should be run only after a clear user request.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill exposes an account-affecting action, auto-bind-coupons, that automatically claims all available coupons without requiring explicit user confirmation or presenting consequences first. Because it operates on the user's authenticated account, accidental or overly eager invocation could modify account state without clear consent, creating an authorization and user-intent mismatch risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.