Moltin

• Outcome: Review
• Latest audit: May 28, 2026 at 1:14 PM UTC
• Version:
  1.0.4

Overview

This Moltin ecommerce skill appears coherent, but it gives broad live-store API mutation authority without clear confirmation or scoping safeguards.

Install only if you intend to let the agent operate on a Moltin/Elastic Path commerce tenant. Before use, require explicit approval for any create, update, patch, or delete request, prefer scoped Membrane actions over raw proxy calls, and test against a non-production store first.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The skill description is broad enough to match generic 'manage data, records, and automate workflows' requests, which can cause the agent to invoke this integration outside clearly ecommerce-specific Moltin tasks. In a skill that can read, modify, or delete external business data, over-broad routing increases the chance of unintended actions against a live tenant.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The proxy request section documents arbitrary direct API access, including POST, PUT, PATCH, and DELETE, but does not warn that these requests may modify or permanently delete Moltin data. Without a caution or confirmation requirement, an agent may use raw requests for convenience and perform high-impact state changes without sufficient user awareness.

VirusTotal

VirusTotal engine telemetry is currently stale for this artifact.