ClawHub

Masterclass Builder

Security checks across malware telemetry and agentic risk

Overview

This tutoring skill stores course lessons and progress locally, which matches its stated purpose and shows no hidden or harmful behavior.

Install if you are comfortable with the skill creating and updating local course files under masterclasses/. Avoid putting secrets or highly sensitive personal details in homework notes, and review any scheduled-delivery cron command before adding it.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill advertises broad natural-language triggers such as 'teach me [topic]' and 'I want to learn [topic]' at the metadata level, which increases the chance of accidental invocation during ordinary conversation. Because the skill performs stateful file writes and lesson-generation workflows once activated, unintended triggering could create or modify user workspace data without clear user intent.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger table includes ambiguous phrases like 'next lesson', 'my courses', 'course progress', and 'resume [topic]' without requiring that the conversation already be inside this skill's context. These are common phrases that may appear in unrelated chats, so the skill could incorrectly activate and read or update course state, causing unintended actions and confusing cross-skill behavior.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal