Back to skill
Skillv1.0.0
ClawScan security
Synaptics · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 17, 2026, 8:58 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only skill that matches its description (providing background and recent news about Synaptics), requests no credentials or installs, and is internally consistent.
- Guidance
- This skill appears safe and coherent, but note the publisher is unknown and there is no homepage. Because it is instruction-only the model may summarize web sources or hallucinate — ask for citations or verify facts against primary sources (Synaptics' official site, regulatory filings, reputable news outlets) before using the information for critical decisions. If you have policies about allowing agents to browse the web, apply them as usual.
Review Dimensions
- Purpose & Capability
- okName, description, and SKILL.md all describe the same purpose (company background, products, global footprint, recent news). There are no unrelated requirements.
- Instruction Scope
- okRuntime instructions are limited to providing background and news; they do not instruct the agent to read files, access environment variables, or transmit data to external endpoints beyond normal web research implied by 'official information and authoritative media.'
- Install Mechanism
- okNo install spec and no code files; nothing is written to disk or installed.
- Credentials
- okThe skill declares no environment variables, credentials, or config paths — proportional to its stated purpose.
- Persistence & Privilege
- okalways is false and there is no request to modify other skills or system-wide settings; autonomy (model invocation) is allowed by default but that is normal and not excessive here.