Aws Well Architected

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.2

Overview

This AWS Well-Architected skill is coherent, but it gives an agent broad authenticated access to change or delete Well-Architected records without explicit approval safeguards.

Install only if you trust Membrane to mediate AWS Well-Architected access. Prefer discovered Membrane actions over raw proxy calls, and require a clear confirmation showing the method, endpoint, connection, body, and expected effect before any POST, PUT, PATCH, or DELETE request.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill explicitly enables direct proxy requests to the AWS Well-Architected API, including destructive HTTP verbs like PUT, PATCH, and DELETE, but provides no warning or confirmation guidance before such calls. In an agent context, this increases the chance of unintended state-changing operations against cloud architecture records, especially if the model falls back to raw requests when actions are unavailable.

VirusTotal

64/64 vendors flagged this skill as clean.