Multi Model Critique

• Outcome: Pass
• Latest audit: May 28, 2026 at 10:17 AM UTC
• Version:
  1.0.1

Overview

The skill does what it says: coordinates selected model agents to critique and improve complex answers, with no evidence of hidden data access or destructive behavior.

Install this if you want complex prompts routed through multiple selected model agents. Avoid sending highly sensitive information unless you trust those agents, set budget and timeout controls for costly runs, and delete generated prompt or run-plan files when they are no longer needed.

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)

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The natural-language instruction "Keep output in Korean unless user asked otherwise" imposes a specific language by default. This is a locale/language policy concern because the skill forces a language choice unless the user explicitly overrides it, rather than offering a neutral default or explicit opt-in.

VirusTotal

66/66 vendors flagged this skill as clean.