Adhd Assistant 1.0.0
Analysis
The skill is coherent and code-free, but it tells the agent to persist sensitive ADHD and treatment information in memory without clear consent, retention, or deletion boundaries.
Findings (2)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
compatibility: Works with OpenClaw memory system and scheduling tools
Scheduling or reminder tools are purpose-aligned for ADHD planning, but calendar/reminder changes can affect the user's routine and should remain user-directed.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
Over time, remember these preferences (via OpenClaw memory): ... Diagnosed or suspected ADHD ... Current treatments (medication, therapy) - for context only
The skill directs the agent to persist sensitive mental-health and treatment information in memory, but the shown artifact does not require explicit consent, define retention limits, or explain how the user can review or delete that memory.
