Back to skill
Skillv1.0.0
ClawScan security
Jarvis Refactor Planner 01 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 5:47 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an instruction-only planning skill for low-risk refactoring workflows and does not request credentials, installation, code execution, persistence, or broad access.
- Guidance
- This skill appears safe to install as a planning aid. As with any development-planning helper, review any generated commands or refactor steps before applying them to a real codebase.
Review Dimensions
- Purpose & Capability
- okThe stated purpose is to help plan refactors with success criteria, checkpoints, quality gates, rollback points, and implementation-ready outputs; the instructions are coherent with that purpose.
- Instruction Scope
- okThe skill provides planning and formatting guidance only, with no instructions to override user intent, bypass review, or perform destructive actions.
- Install Mechanism
- okThere is no install specification and no code files; the skill is instruction-only.
- Credentials
- okNo binaries, environment variables, credentials, config paths, network services, or local file access are required.
- Persistence & Privilege
- okThe artifacts show no persistence mechanism, background activity, credential use, account authority, or privileged access.