Wiza

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

Overview

This Wiza skill is a coherent integration, but it gives an agent broad authenticated API access without clear confirmation guardrails for write or delete actions.

Install only if you are comfortable granting Membrane delegated access to Wiza. Before any create, update, patch, delete, or raw proxy request, ask the agent to show the exact endpoint, HTTP method, and payload, and confirm the action yourself. Prefer listed Membrane actions over raw proxy calls where possible.

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: 88% confidence
• Finding: The skill explicitly instructs the agent to issue direct proxy requests to the external Wiza API, but does not require a user-facing warning or confirmation before transmitting data. In an agent setting, this can lead to sensitive prompts, identifiers, or business data being sent to a third-party service without sufficiently explicit user awareness.

VirusTotal

63/63 vendors flagged this skill as clean.