Back to skill
Skillv1.0.0
ClawScan security
Scene Transition Library · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 28, 2026, 11:32 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- An instruction-only prompt/reference library for scene transitions whose requirements and instructions match its stated purpose and show no signs of unexpected access or network activity.
- Guidance
- This skill appears coherent and low-risk: it’s an instruction-only prompt/reference pack for writing scene-transition prompts and uses only the included local files. Before installing, you may want to confirm the publisher/source (none provided) if provenance matters for your organization, and review sample outputs for quality and any unintended content. Because it’s an autonomous-capable skill by default, monitor initial outputs the agent generates until you’re comfortable with its behavior.
Review Dimensions
- Purpose & Capability
- okThe skill is a prompt/reference library for film/video transition wording. It requests no binaries, credentials, or config paths — everything present (SKILL.md and two reference files) is consistent with that purpose.
- Instruction Scope
- okRuntime instructions are limited to providing formatting rules, prompt-writing guidelines, and referencing the included local reference files. There are no instructions to read arbitrary system files, access environment variables, or call external endpoints.
- Install Mechanism
- okNo install spec and no code files — instruction-only. This minimizes disk writes and execution of third-party code.
- Credentials
- okNo environment variables, secrets, or credentials are declared or used. The skill does not request access to unrelated services or configs.
- Persistence & Privilege
- okThe skill is not forced-always, does not claim extra privileges, and contains no instructions to modify other skills or system-wide settings.