ClawHub
Back to skill

Security audit

Personal Productivity

Security checks across malware telemetry and agentic risk

Overview

This appears to be a Chinese-language productivity or focus skill with routing and language-scope weaknesses, but no evidence of hidden access, persistence, credential use, or destructive behavior.

Install this if you want a Chinese-language productivity or focus-coaching skill. Before installing, check that its trigger wording is narrow enough for your workflow and that Chinese-only responses are acceptable; no evidence here shows unsafe access or hidden behavior.

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
89% confidence
Finding
The trigger description is broad enough to match many common productivity, planning, focus, and procrastination queries, which can cause the skill to activate more often than intended. Over-broad activation is a security and safety concern because it increases unintended routing, may overshadow more appropriate skills, and can cause the system to solicit or process user work/life details outside a narrowly scoped context.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
The skill content is entirely in Chinese without stating a locale restriction or offering a language fallback, which can lead to mismatched activation and confusing or unusable responses for non-Chinese-speaking users. This is mainly a scope and routing weakness rather than a direct exploit, but it can degrade trust, cause inappropriate skill selection, and make downstream behavior less predictable.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.