Back to skill
Skillv1.0.0

ClawScan security

modern-life-mentor · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 29, 2026, 11:45 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
This is an instruction-only life-coaching skill whose declared purpose, content, and resource requirements are internally consistent: it asks for no credentials, installs, or system access and confines itself to counseling frameworks and local reference material.
Guidance
This skill appears coherent and low-risk from a technical standpoint because it is instruction-only and asks for no credentials or installs. Before enabling it, note: (1) content risk — it's an advice/mentoring tool, not a substitute for professional medical/mental-health or legal advice; for serious issues consult a qualified professional; (2) privacy — conversations with the skill may be logged by your agent platform, so avoid pasting highly sensitive personal data (SSNs, full medical histories, account passwords); (3) provenance — source/homepage is unknown and references PDFs are bundled by name only, so verify any quoted facts or copyrighted material independently if that matters to you; (4) autonomy — the skill may be invoked by the agent when eligible (normal behavior); if you prefer manual control, adjust your agent's skill invocation settings.

Review Dimensions

Purpose & Capability
okThe name and description (modern life / thought frameworks for career, relationships, meaning) match the SKILL.md and references. Nothing in the bundle requests cloud credentials, system binaries, or unrelated capabilities that would be unnecessary for a coaching/mentoring skill.
Instruction Scope
okRuntime instructions are limited to listening, classifying the problem type, applying the documented theoretical frameworks, and producing guiding suggestions. The SKILL.md does not instruct the agent to read arbitrary files, env vars, or contact external endpoints beyond using its own conversational output. The skill references local documentation files under references/, which is coherent for an instruction-only skill.
Install Mechanism
okThere is no install spec and no code files to execute — lowest-risk form. Nothing is downloaded or written to disk by the skill itself.
Credentials
okNo environment variables, credentials, or config paths are required. The declared requirements are minimal and proportionate to a purely instructional coaching skill.
Persistence & Privilege
okalways is false and the skill does not request elevated or permanent presence, nor does it modify other skills or system-wide settings. It can be invoked autonomously (default platform behavior), which is expected for skills and not a standalone concern here.