Back to skill
Skillv1.0.0
ClawScan security
Skylv Task Planner · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 21, 2026, 6:02 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only task-planning assistant whose requests and instructions are consistent with its stated purpose and it does not ask for extra system access or credentials.
- Guidance
- This skill is instruction-only and low-risk from a system-access perspective, but review outputs before acting—plans and estimates can be incorrect or incomplete. Do not paste secrets or sensitive credentials into prompts. If you have policy concerns about an assistant using skills autonomously, consider restricting autonomous invocation or reviewing the agent's permissions first.
Review Dimensions
- Purpose & Capability
- okThe skill name and description are a task planner; the SKILL.md contains only templates, examples, and prompt guidance for breaking down tasks, estimating time, and tracking progress—everything requested is appropriate for a planner.
- Instruction Scope
- okRuntime instructions are limited to generating plans, timelines, estimates, and progress calculations. They do not reference reading files, accessing environment variables, contacting external endpoints, or otherwise collecting unrelated system data.
- Install Mechanism
- okNo install spec and no code files are present (instruction-only), so nothing is written to disk or installed by the skill itself.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths; there are no disproportionate requests for secrets or unrelated credentials.
- Persistence & Privilege
- okThe skill does not request always:true and does not attempt to modify other skills or system configuration; autonomous model invocation is allowed by platform default but is not extended by this skill.