ClawHub
Back to skill

Security audit

Self Improving Life

Security checks across malware telemetry and agentic risk

Overview

This life-assessment skill is mostly purpose-aligned, but its helper script automatically saves sensitive personal assessment details to a local file without asking first.

Install only if you are comfortable with local assessment files being created. Before running the script, consider using it in a private directory, deleting the generated report afterward if you do not need it, or editing the script to print results without saving.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The script writes a detailed self-assessment report containing personal wellness, relationship, and work data to disk without making that persistence explicit before collection. This creates a privacy risk because sensitive personal reflections may remain on shared systems, be included in backups, or be read by other local users or processes.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The script stores sensitive self-assessment data locally without prior warning or consent, despite handling information about health, relationships, and work-life balance. In the context of a life-coaching skill, users may reasonably expect an ephemeral assessment, so silent persistence increases the chance of unintended disclosure.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.