ClawHub

reshape-your-life（重塑你的人生）

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese guided self-reflection skill with no code or system access, though its coaching style is broad and directive.

Use this as a structured reflection exercise, not as mental-health, legal, financial, career, or relationship advice. Install it only if you are comfortable with Chinese-language coaching prompts and with sharing personal reflections in the chat; seek qualified human support for crisis situations or major life decisions.

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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation criteria are broad enough to match very common statements about stress, confusion, or dissatisfaction, so the skill may trigger in situations where the user did not ask for this kind of deep life-planning intervention. In a sensitive self-help context, unintended activation can steer conversations toward identity, mission, and meaning without clear consent, creating a risk of overreach and inappropriate influence.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The skill content hardcodes a Chinese opening script and interaction flow without offering a user language check or fallback, which can cause mismatched-language responses and reduce user comprehension. While not a classic security exploit, this becomes a safety and reliability issue because users may receive emotionally directive guidance in a language they do not understand well.

Natural-Language Policy Violations

Low
Confidence
90% confidence
Finding
The skill content is entirely in Chinese without any visible language selection, detection, or user opt-in. This can cause users to misunderstand guidance, consent to an interaction they cannot fully comprehend, or receive ineffective advice, especially in a reflective life-planning context where clarity and nuance matter.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal