Back to skill
Skillv1.0.3
ClawScan security
Batch Content Sprint Os · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 11, 2026, 8:41 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only planning skill for running weekly content sprints; its declared purpose, instructions, and requirements are coherent and do not request credentials, installs, or external access.
- Guidance
- This skill is low-risk: it's instruction-only and asks for no credentials or installs. Before using, note the license (CC BY-NC-SA 4.0): non-commercial reuse is permitted with attribution, but commercial use requires a paid license from Razestar. Also verify any outputs you generate (task assignments, timelines) against your actual team availability — the skill provides a template and heuristics but not automated checks against real calendars or systems.
Review Dimensions
- Purpose & Capability
- okThe name and description (weekly content sprint planning) match the SKILL.md workflow: defining constraints, building a backlog, time-blocking, and producing a sprint board. No unrelated capabilities or privileges are requested.
- Instruction Scope
- okThe runtime instructions are limited to planning tasks and producing a sprint board/outputs. They do not instruct reading system files, environment variables, network endpoints, or transmitting data externally.
- Install Mechanism
- okNo install spec or code is provided (instruction-only), so nothing will be written to disk or downloaded during install.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths — consistent with a purely instructional planning tool.
- Persistence & Privilege
- okalways is false and the skill is user-invocable (normal). Model invocation is allowed by default, which is expected for skills of this type and is not combined with other risky privileges.