ClawHub
Back to skill

Security audit

Mbti Coach Suite

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk MBTI coaching guide that asks preference questions and routes users to related coaching skills without code execution, credentials, or system access.

Install this as personality-coaching content, not professional mental-health or career advice. Review any child coach skills separately before using them, especially if they ask for more personal context or make stronger recommendations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
88% confidence
Finding
The trigger description is broad enough to activate on common MBTI-related conversation, even when the user may only want general discussion rather than being routed into this skill. Over-broad routing can cause inappropriate skill invocation, reduce user control, and increase the chance of follow-on exposure to less suitable or lower-quality subskills.

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The skill is written to present and guide interactions in Chinese without checking the user's language preference. This can cause misleading or inaccessible responses for users expecting another language, which is a quality and consent issue that may result in misunderstanding of advice or incorrect downstream skill selection.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.