Back to skill
Skillv1.0.0

ClawScan security

A search for forklift design ers · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 20, 2026, 5:42 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is an instruction-only forklift Q&A helper that only instructs web searches and local reference documents; its declared requirements and behavior are coherent with its stated purpose.
Guidance
This skill is low-risk: it uses public web searches and bundled reference notes to answer forklift questions and does not request credentials or install code. Before installing, consider: (1) the skill will fetch public webpages (search results, brand sites, WeChat articles) — do not provide sensitive or private data to it; (2) web-sourced answers may be out of date or inaccurate, so cross-check critical technical or safety-related recommendations against official manuals or certified technicians; (3) if you see the skill later requesting credentials, system access, or an install step, treat that as a new risk. Overall, the package appears coherent with its stated purpose.

Review Dimensions

Purpose & Capability
okName/description (forklift Q&A) match the instructions and bundled reference files (brand sites, standards, WeChat articles). No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
okSKILL.md tells the agent to use search engines, brand websites, industry sites, and a specific WeChat public account — all reasonable data sources for this domain. There are no instructions to read system files, environment variables, or to send data to unexpected external endpoints.
Install Mechanism
okNo install spec and no code files (instruction-only). Nothing will be written to disk or fetched during an install step, minimizing installation risk.
Credentials
okThe skill requests no environment variables, credentials, or config paths. This is proportional to a read-only information/research skill.
Persistence & Privilege
okalways is false and the skill does not request elevated/persistent privileges or modify other skills. Autonomous invocation is allowed (platform default) and is not combined with other red flags.