ClawHub

NBTI

Security checks across malware telemetry and agentic risk

Overview

This is a self-contained Chinese meme personality quiz with no code execution, credential access, networking, or persistence.

Install this as an entertainment quiz, not a real mental-health or personality assessment. Be aware it may activate on broad NBTI or mental-state mentions, uses Chinese-only output, and contains edgy mental-health humor, but it does not ask for sensitive access or run code.

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
93% confidence
Finding
The trigger phrases are broad enough that the skill may activate during ordinary conversation about personality tests, mental state, or when discussing someone else's NBTI result, even if the user did not intend to launch the skill. Unintended activation can disrupt user experience, hijack conversational flow, and cause the agent to steer users into an 8-question interaction without clear consent.

Natural-Language Policy Violations

Medium
Confidence
78% confidence
Finding
The skill explicitly requires Chinese for both questions and results without offering fallback behavior or checking the user's language preference. This can cause exclusion, confusion, or degraded usability for users interacting in other languages, especially if the skill is triggered accidentally.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal