ClawHub
Back to skill

Security audit

mcd-cn

Security checks across malware telemetry and agentic risk

Overview

This McDonald's skill appears purpose-aligned, but it can automatically claim coupons on the user's account without a clear confirmation step.

Review before installing. The main risk is not malware or exfiltration; it is that the agent may claim McDonald's coupons on your account too easily. Only use it if you are comfortable providing MCD_TOKEN to this integration, and instruct your agent to ask for explicit confirmation before any coupon-claiming action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrases for coupon claiming are broad enough that an agent could interpret ordinary conversational language as consent to perform an account-affecting action. In this skill context, the action modifies the user's McDonald's account by claiming coupons, so ambiguous invocation can lead to unintended state changes without sufficiently explicit authorization.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill exposes an automatic account-affecting action that claims all available coupons, but it does not require a warning or explicit confirmation before modifying the user's account state. In the context of an agent that may autonomously follow trigger phrases, this increases the risk of unauthorized or accidental actions taken on behalf of the user.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.