Back to skill
Skillv1.0.0

ClawScan security

intimate-ch14-maintenance-repair · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 20, 2026, 5:45 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
This is an instruction-only teaching assistant for Chapter 14 of Miller's Intimate Relationships textbook that only reads its bundled reference files and requests no installs, credentials, or external access.
Guidance
This skill appears coherent and low-risk: it only uses the bundled chapter reference files and provides teaching guidance. Before installing, note that (1) it is educational—not a substitute for professional therapy or safety planning, and it explicitly advises contacting emergency services for danger; (2) it includes textbook-derived material—if you care about copyright or licensing, verify you have rights to distribute or use that content; and (3) while it requests no secrets or external network access, exercise usual caution granting any skill autonomous invocation if you have platform-specific policy concerns.

Review Dimensions

Purpose & Capability
okThe name/description (teaching Chapter 14: maintaining and repairing relationships) matches the provided SKILL.md and the ten reference files; there are no unrelated requirements (no env vars, binaries, or config paths).
Instruction Scope
okRuntime instructions restrict behavior to progressive disclosure and reading the local references/ files on demand; they do not instruct the agent to read other system files, access external endpoints, or exfiltrate data. Safety boundary guidance (e.g., refer dangerous situations to emergency services) is explicit.
Install Mechanism
okNo install spec and no code files—this is instruction-only, so nothing is downloaded or written to disk by an installer.
Credentials
okThe skill requests no environment variables, credentials, or external configuration—proportional to an educational assistant that only uses bundled reference documents.
Persistence & Privilege
okalways is false and the skill does not request elevated or persistent privileges or attempt to modify other skills; normal autonomous invocation (disable-model-invocation: false) is set but is not combined with other risks.