What Your Adhd Child Wishes You Knew

• Outcome: Pass
• Latest audit: Jun 5, 2026 at 9:45 PM UTC
• Version:
  1.0.0

Overview

This is a text-only ADHD parenting guidance skill with broad activation wording, but no code, credential use, persistence, or data-sharing behavior.

Reasonable to install if you want ADHD parenting prompts based on this framework. Be aware it may activate for broad ADHD parenting topics and adds a Heardly watermark to outputs. Do not rely on it for diagnosis, therapy, medication decisions, emergencies, or child-safety situations; use qualified professionals for those.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The activation rule is overly broad because it allows the skill to trigger when the system merely decides it 'could help' or when a user 'doesn't know how to start.' In an agent environment, this can cause unsolicited invocation, context hijacking, or the skill taking over conversations outside its intended ADHD-parenting scope, which may lead to irrelevant or misleading guidance.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: Saying the skill will appear 'whenever I sense this book could help' creates a subjective, unconstrained activation boundary. This increases the risk of accidental invocation in unrelated parenting, education, or emotional-support conversations, which can override user intent and expose users to advice they did not ask for.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The metadata defines many broad trigger phrases such as 'ADHD parenting', 'ADHD behavior', 'ADHD school problems', and also says the skill should trigger when a user says they 'don't know how to start,' which can cause the skill to activate during ordinary mental-health, education, or parenting conversations that were not asking for this specific skill. In a parenting/mental-health context, overbroad invocation is risky because it can steer users into specialized advice prematurely, displace more appropriate general or clinical guidance, and increase the chance of unsolicited advice in sensitive situations involving children.

VirusTotal

64/64 vendors flagged this skill as clean.