Assembled

• Outcome: Review
• Latest audit: May 29, 2026 at 9:36 PM UTC
• Version:
  1.0.2

Overview

This looks like a legitimate Assembled integration, but it exposes broad authenticated API access that could modify tenant data without clear confirmation guardrails.

Install only if you trust the publisher and are comfortable giving the agent Membrane-mediated access to your Assembled tenant. Before using it, require the agent to prefer read-only/prebuilt actions, show the exact endpoint and payload, and get explicit confirmation before any create, update, delete, scheduling, workflow, or configuration change.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill explicitly documents a generic authenticated proxy that supports POST, PUT, PATCH, and DELETE without any guardrails, warnings, or confirmation requirements for state-changing requests. In an agent setting, this increases the risk of accidental or prompt-induced destructive actions against the Assembled tenant, especially when the model falls back to raw requests instead of curated actions.

VirusTotal

65/65 vendors flagged this skill as clean.