Make Commerce

Security checks across malware telemetry and agentic risk

Overview

This is a real Make Commerce integration, but it gives an agent broad authenticated control over commerce data without clear guardrails for high-impact changes.

Review before installing. Use a least-privilege Make Commerce account, prefer predefined Membrane actions over raw proxy calls, and require explicit approval before any write, delete, purchase, refund, order-management, customer-data, or payment-related action. Consider pinning or reviewing the Membrane CLI version instead of blindly using @latest.

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 (1)

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The skill description is very broad ('Manage data, records, and automate workflows') and provides little constraint on when the skill should be invoked. In an agent setting, overly broad routing language can cause the skill to be selected for ambiguous requests, leading to unintended external actions against commerce systems or unnecessary exposure of connected data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal