ADHD Assistant
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: adhd-assistant Version: 1.0.0 The skill, an ADHD assistant, requests to learn sensitive personal health information, specifically 'Current treatments (medication, therapy)', for context. While the `SKILL.md` explicitly states this data is 'for context only' and includes strong safety constraints against providing medical advice or diagnosis, the collection of such sensitive information by an AI agent, even for a stated benign purpose, represents a privacy risk. There is no evidence of intentional malicious behavior like data exfiltration, unauthorized execution, or persistence.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Private health-related information could be saved and reused in later interactions beyond the current task.
The skill directs the agent to store mental-health and treatment-related details in persistent memory, but the visible instructions do not require explicit consent, limit the detail stored, define retention, or explain deletion/review controls.
Over time, remember these preferences (via OpenClaw memory): ... Diagnosed or suspected ADHD ... Current treatments (medication, therapy) - for context only
Only store sensitive ADHD, diagnosis, medication, or therapy details after explicit user consent; keep entries minimal; tell users how to review, update, and delete them.
The assistant may help create reminders, check-ins, or time blocks; these should be user-directed to avoid unwanted schedule changes.
Scheduling tools are purpose-aligned for reminders and daily planning, but they can affect a user's calendar or routine if used without confirmation.
compatibility: Works with OpenClaw memory system and scheduling tools
Confirm with the user before creating, changing, or deleting reminders, check-ins, calendar events, or recurring routines.