Back to skill
Skillv1.0.0
ClawScan security
improvement-planner · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 1:45 PM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This instruction-only skill creates improvement plans and does not request credentials, run code, or directly change files or accounts.
- Guidance
- This skill appears safe to install as a planning aid. Review the improvement plan it produces before allowing any suggested follow-on agents or implementation work to make changes.
Review Dimensions
- Purpose & Capability
- okThe stated purpose is coherent: it reviews a prior project analysis, prioritizes improvements, assigns suggested agents, and produces a plan.
- Instruction Scope
- okInstructions are bounded to planning and documentation, and the skill states the plan will be presented to the user for approval before execution.
- Install Mechanism
- okThere is no install spec, no required binaries, no environment variables, and no code files to execute.
- Credentials
- okThe artifacts do not request local system access, network access, credentials, privileged configuration, or external services.
- Persistence & Privilege
- okNo persistence, background execution, credential use, or privilege escalation is described.