ClawHub

ADHD Support

Security checks across malware telemetry and agentic risk

Overview

The skill appears to provide conversational ADHD and executive-function support without system access, persistence, or data exfiltration behavior.

This is reasonable to install if you want conversational ADHD or executive-function support. Be aware that it may activate on broad productivity or overwhelm language, and treat its Crisis Mode as task-support coaching only, not medical, mental-health, or emergency help.

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

High
Confidence
95% confidence
Finding
The trigger language is extremely broad and is designed to activate on common productivity, stress, and planning requests, not just ADHD-related scenarios. In context, this can cause the skill to inappropriately engage in quasi-mental-health guidance for users who may need a different workflow or more bounded support, increasing the chance of misclassification and overreach.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill defines a 'Crisis Mode' for users expressing paralysis, overwhelm, or shame spirals but provides no boundary-setting that it is not a substitute for professional or emergency mental-health care. Because the skill operates in a psychologically sensitive context and instructs the agent to prioritize crisis handling, users with escalating distress may receive only task-support coaching when they may actually need human or emergency intervention.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal