Skillv1.0.0

ClawScan security

Corning · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 23, 2026, 7:07 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only informational briefing about Corning (history, products, market position) and it does not request credentials, install code, or instruct the agent to access system resources.
Guidance: This skill is a read-only briefing and appears internally consistent. Before relying on figures or historical claims for decisions, cross-check them against primary sources (investor reports, company filings, or trusted histories) since SKILL.md may contain simplifications or minor inaccuracies. If you prefer to limit automatic use of skills, you can disable autonomous invocation for skills in your agent settings; otherwise this skill poses minimal risk because it requests no credentials or installs.

Purpose & Capability: okThe skill name, description, and SKILL.md all describe the same purpose: an expert briefing about Corning and its glass technologies. There are no unrelated required binaries, env vars, or config paths.
Instruction Scope: okSKILL.md contains static content (timeline, business analysis, facts) and 'read_when' triggers for when to use the briefing. It does not instruct the agent to read files, access environment variables, call external endpoints, or collect/transmit system data.
Install Mechanism: okNo install spec and no code files are present; this is instruction-only, which is the lowest install risk (nothing is written to disk or executed).
Credentials: okThe skill declares no required environment variables, credentials, or config paths. It does not request any sensitive tokens or system-level access.
Persistence & Privilege: okalways is false (no forced inclusion). Model invocation is allowed (default) but that is normal for skills and acceptable here because the skill does not request elevated privileges or secrets.