怎样解题

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:42 PM UTC
• Version:
  1.0.3

Overview

This is a low-risk Chinese problem-solving guide that only changes how the assistant asks questions and does not request system access or sensitive data.

Before installing, consider whether you want common phrases like “help me analyze this” or “help me plan” to trigger a step-by-step questioning style instead of a direct answer. No sensitive permissions or execution behavior are evident in the artifacts.

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: 95% confidence
• Finding: The trigger phrases are broad conversational requests such as '帮我分析这个问题' and '帮我规划一下', which can match many ordinary interactions unrelated to this skill’s intended scope. This can cause unintended activation, leading the agent to switch into the skill’s constrained Socratic behavior at inappropriate times and potentially disrupt safer or more suitable handling of user requests.

VirusTotal

64/64 vendors flagged this skill as clean.