咨询级智能分析系统

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:31 PM UTC
• Version:
  1.0.0

Overview

This is a disclosed research and reporting helper with broad triggers, but no evidence of hidden access, persistence, credential use, or unsafe actions.

Install this if you want a general-purpose Chinese-language analysis/reporting workflow. Be aware it may activate on broad phrases like “analyze this” or “make a report,” so give explicit instructions when you want a lighter answer, no web research, or a different language/source preference.

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: 93% confidence
• Finding: The skill advertises activation on very common phrases like “分析一下”, “深度研究”, “帮我调研”, and “做个报告”, which are broad requests that can appear in many unrelated conversations. This can cause unintended invocation of the skill, expanding its scope to contexts the user did not explicitly request and increasing the chance of unnecessary web access, over-collection of data, or misaligned behavior.

VirusTotal

63/63 vendors flagged this skill as clean.