ClawHub
Back to skill

Security audit

Learning Tutor

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only tutoring skill whose behavior matches its learning-support purpose, with mild cautions about broad routing and personalization.

Reasonable to install if you want a general learning tutor. For medical, legal, financial, or other high-stakes subjects, prefer a specialized skill or ask for careful source-based caveats. Avoid sharing unnecessary personal details, since the tutor is designed to adapt to your demonstrated knowledge and interests.

SkillSpector

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
91% confidence
Finding
The skill description is extremely broad ('any domain' and many common learning tasks), making it likely to be invoked in situations better handled by more specialized or safer skills. Overbroad routing can expose users to lower-quality or inappropriate assistance, especially in regulated, high-risk, or domain-specific contexts where tailored safeguards are needed.

Static analysis

No suspicious patterns detected.