Qa Ai Output Critique

• Outcome: Pass
• Latest audit: Jun 20, 2026 at 7:53 PM UTC
• Version:
  1.3.0

Overview

This is a read-only QA critique skill that provides structured review templates and does not show hidden, destructive, or data-exfiltrating behavior.

Install this if you want structured QA review of AI-generated test cases. Be aware that its trigger phrases are somewhat broad, so confirm it is being used for critique or test-review tasks when asking general questions like what is wrong or how to improve.

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 (1)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The activation trigger examples are broad everyday phrases like '评估这个输出' and '有什么问题', which can cause this skill to activate in many normal conversations that are not specifically requesting structured QA critique. Over-broad activation increases the chance of unintended routing, causing the assistant to apply the wrong workflow, expose irrelevant internal critique logic, or interfere with higher-priority task handling.

VirusTotal

63/63 vendors flagged this skill as clean.