Multi-model automatic fallback system

• Outcome: Pass
• Latest audit: May 28, 2026, 10:17 AM
• Version:
  1.0.0

Overview

This skill appears to provide legitimate model fallback behavior, but users should understand that fallback may send prompts to alternate model providers.

Before installing, review which model providers are configured for fallback and avoid enabling providers that are not approved for confidential or regulated prompts. Disable or narrow fallback for sensitive work if the skill does not provide clear provider controls.

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: This is a real security and privacy issue because the skill explicitly routes requests across multiple third-party model providers, but the description does not warn users that their prompts and potentially sensitive data may be transmitted to alternate external services during fallback. In a fallback system, provider switching can happen automatically and invisibly, which increases the risk of unintended data disclosure, compliance violations, and trust breakdown if users assume requests stay with the primary provider.

VirusTotal

66/66 vendors flagged this skill as clean.