Back to skill
Skillv1.0.0
ClawScan security
HTML Designer · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 10, 2026, 1:42 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only HTML/CSS design helper that only includes local reference docs and template assets and requests no credentials, installs, or unusual system access — its declared purpose matches its footprint.
- Guidance
- This skill is instruction-only and bundles HTML templates and design reference docs — it doesn't ask for credentials or install code. Before enabling: review the included templates if you care about copyrights or proprietary content; be aware that when the agent uses this skill it will process any prompt text you provide (as with any skill) — avoid sending secrets in prompts. If you allow autonomous agent actions, remember the agent may call the skill when it thinks appropriate; that is normal but only relevant if you have strong concerns about automated runs.
Review Dimensions
- Purpose & Capability
- okName/description (HTML/CSS web design) align with the provided files (HTML templates and design references). There are no declared env vars, binaries, or config paths that don't belong to a design/template skill.
- Instruction Scope
- okSKILL.md instructs the agent to act as a designer and to use the included references and templates. It does not instruct reading unrelated system files, contacting external endpoints, or accessing credentials. The scope is constrained to creating HTML/CSS designs and using bundled assets/references.
- Install Mechanism
- okNo install specification or external downloads — instruction-only skills carry low install risk. All assets are local template and documentation files.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths. This is proportionate for a design/template skill.
- Persistence & Privilege
- okalways is false and there is no special persistent/system modification requested. The skill can be invoked autonomously by the agent (platform default), which is expected for a functional skill and not by itself a concern.