ClawHub
Back to skill

Security audit

麦当劳智能点餐助手

Security checks across malware telemetry and agentic risk

Overview

The skill is transparent and mostly purpose-aligned, but it combines McDonald's account-token use with broad shell execution and an overrideable API endpoint for sensitive requests.

Review before installing. Use it only if you trust the publisher and are comfortable giving the skill a McDonald's account token plus shell-based curl access. Keep MCD_MCP_URL unset or pointed only at the official mcp.mcd.cn endpoint, do not run it unattended, and require explicit confirmation before coupon claiming, address creation, coupon use, or order creation.

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)

External Transmission

Medium
Category
Data Exfiltration
Content
## API Call Pattern

All tools are invoked via curl to the MCP endpoint:

```bash
curl -s -X POST "${MCD_MCP_URL:-https://mcp.mcd.cn}" \
Confidence
90% confidence
Finding
The skill explicitly sends authenticated requests containing the Bearer token to an external endpoint via curl, and the endpoint can be overridden by the MCD_MCP_URL environment variable. This creates a real data exfiltration and credential exposure risk if the endpoint is misconfigured, maliciously redirected, or insufficiently validated, even though external API use is functionally expected for this skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.