ClawHub
Back to skill

Security audit

Study Tutor

Security checks across malware telemetry and agentic risk

Overview

This is a study-tutoring instruction skill with disclosed, bounded study-note persistence and no executable code.

Install only if you are comfortable with a study profile being saved for continuity. Point it only at study materials you want used, avoid sharing sensitive personal details, and review or delete memory/{subject}-study.md if you do not want retained learning history.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The README states that the skill maintains a cross-session study record under memory/{subject}-study.md, but it does not clearly disclose that user learning data may be written and retained. This can lead to unexpected persistence of potentially sensitive educational data, creating privacy and consent risks, especially over repeated sessions.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.