ClawHub
Back to skill

Security audit

软考高级真题与模拟题

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Ruankao exam-question lookup skill with some broad trigger wording but no evidence of hidden, destructive, or data-stealing behavior.

Reasonable to install for Ruankao advanced exam preparation. Be aware it may activate on generic Chinese study phrases and may run read-only GitHub CLI API commands or fetch public web pages; confirm the query is about Ruankao if it triggers unexpectedly.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes broad phrases like '历年真题', '刷题', '模拟题', and '搜索真题' that can easily match ordinary study-related requests outside the intended narrow scope of this skill. Because the skill has access to exec, web_search, web_fetch, and read, accidental invocation could cause unnecessary tool use, incorrect routing, or unintended retrieval of external content for users who did not specifically request this skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.