ClawHub

Make Change That Lasts 9 Simple Ways To Break Free From The Habits That Hold You Back

Security checks across malware telemetry and agentic risk

Overview

This is a self-help book-summary skill with no executable code or hidden access, but users should not treat its health-adjacent advice as medical or mental-health care.

Install only if you want a self-help summary and reflection assistant. Treat its health-related content as general book-based guidance, not a substitute for a clinician, therapist, diagnosis, or treatment plan, especially for symptoms, chronic illness, anxiety, depression, trauma, crisis, or worsening health concerns.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill is configured to proactively present behavior-change and wellbeing guidance on first load, but it does not clearly warn users that the content is informational and not a substitute for medical or mental-health care. In a self-help and health-adjacent context, users may over-rely on the advice for anxiety, depression, trauma, or other clinical issues, delaying appropriate professional support.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The line explicitly presents a medical scenario where a patient researches symptoms online and then 'learns to trust her intuition,' with no qualification to seek professional evaluation or treat self-assessment as limited. In a health-adjacent self-help skill, this can encourage users to delay diagnosis, dismiss clinical advice, or make unsafe medical decisions based on incomplete information.

VirusTotal

49/49 vendors flagged this skill as clean.

View on VirusTotal