Databricks

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

Overview

This looks like a legitimate Databricks integration, but it gives an agent broad authenticated Databricks control without clear confirmation guardrails.

Install only if you trust Membrane and intend to let an agent operate against Databricks through your authenticated account. Use a least-privilege Databricks identity, explicitly approve every create/update/delete/run/proxy request, avoid broad table/file access unless needed, and revoke the Membrane connection when finished.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (2)

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill description is broad enough that an agent could invoke it for many loosely related requests involving data, workspaces, or analytics. In a powerful integration like Databricks, over-broad routing increases the chance of unnecessary access to external systems and accidental execution of sensitive operations.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill advertises destructive capabilities such as starting, stopping, editing, and running infrastructure or jobs without any warning, approval requirement, or safety constraints. In Databricks, these actions can disrupt production workloads, incur cost, alter compute configuration, or trigger unintended data-processing side effects if invoked too casually.

VirusTotal

60/60 vendors flagged this skill as clean.