ClawHub
Back to skill

Security audit

My Mcdonald

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward McDonald's helper, but users should confirm before letting it claim coupons on their account.

Install only if you are comfortable giving the agent a McDonald's MCP token. Keep MCD_TOKEN private, avoid changing MCD_MCP_URL unless you trust the destination, and require explicit approval before running the one-click coupon claiming action.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The instruction to use this skill for any McDonald's-related question is overly broad and can cause inappropriate tool invocation when a simple conversational answer would suffice. Broad routing increases the chance of unnecessary external requests, token use, and accidental invocation of higher-risk actions in adjacent flows.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases for auto-bind-coupons are broad and map directly to an account-changing action without requiring a confirmation step. This is dangerous because a casual or ambiguous user request could cause unintended redemption or account modification on the user's behalf.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill presents automatic coupon claiming as a standard capability without a prominent warning that it changes the user's account state. Lack of upfront disclosure can mislead users and downstream agents into treating a state-changing operation like a read-only query, increasing the risk of unauthorized or unintended actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.