ClawHub
Back to skill

Security audit

📝 应用题数学建模教练

Security checks across malware telemetry and agentic risk

Overview

This is a coherent math tutoring skill that guides students through word-problem modeling and does not request risky system, data, network, or execution access.

Before installing, expect this skill to steer math word-problem conversations into a guided questioning style rather than directly solving equations. Review any companion learning or error-tracking skills separately if you care about how student progress is stored.

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
89% confidence
Finding
The activation rule says that whenever a scenario involves word-problem comprehension, mathematical modeling, or setting up equations, the skill 'must' be invoked. This is overly broad and mandatory, which can cause the orchestration layer to route many loosely related requests into this skill even when it is unnecessary or less appropriate. In practice, that can degrade agent behavior, override user preference, and create prompt-routing risk through unintended invocation scope.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.