Back to skill
Skillv1.0.0

ClawScan security

ADHD external brain · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 29, 2026, 1:18 PM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's instructions, required resources, and behavior are internally consistent with a bilingual ADHD-focused planning/remembering assistant and do not request unrelated credentials or installs.
Guidance
This skill appears coherent and does not request unrelated credentials or installs. Before installing or enabling persistent use, ask the author or platform: (1) where Memory_Box / Task_Pool are stored (ephemeral chat memory vs external storage), (2) how long data is retained and how to delete or export it, and (3) whether the agent will send reminders autonomously and how to control frequency. Avoid entering passwords, payment details, or other sensitive secrets into the tool's memory fields until you confirm storage and retention policies.

Review Dimensions

Purpose & Capability
okName/description (ADHD external brain) match the SKILL.md: capturing thoughts, adaptive scheduling based on an energy level, reminders, suspension, and daily rhythm. No unrelated binaries, env vars, or installs are requested.
Instruction Scope
okRuntime instructions are narrowly scoped to conversational behavior (maintain Energy_Level, Task_Pool, Memory_Box; save items; generate suggestions and reminders). The instructions do not reference filesystem paths, external endpoints, or unrelated environment variables.
Install Mechanism
okInstruction-only skill with no install spec and no code files — lowest-risk install footprint. Nothing will be downloaded or written by an installer step.
Credentials
okThe skill declares no required env vars, secrets, or credentials. The requested data (tasks, energy level, memories) are user-provided conversational inputs and are proportionate to the stated purpose.
Persistence & Privilege
noteThe skill expects to maintain Task_Pool and Memory_Box in context, but SKILL.md does not specify where or how data is persisted across sessions (ephemeral convo memory vs long-term storage). Autonomous invocation is permitted by default but always:false. Verify how long notes are retained, where they are stored, and how to delete/export them.