Skillv1.0.0

ClawScan security

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

BenignApr 28, 2026, 10:05 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is a self-contained, instruction-only reference about IWC Schaffhausen; it asks for no credentials, installs nothing, and its instructions are limited to when the agent should consult the reference.
Guidance: This skill appears to be a harmless content reference and is internally consistent. Before installing, decide if you trust the unknown source and whether you need provenance or citations (the SKILL.md appears comprehensive but the origin is unspecified). Also consider: the skill may contain historical or commercial claims that could be out of date or incomplete — verify any details you need for critical decisions against primary sources (IWC, Richemont, reputable watch historiography). No credentials or system access are required, so the security risk is minimal.

Purpose & Capability: okThe name and description match the SKILL.md content: the skill is a factual reference about IWC Schaffhausen. It does not request unrelated resources (no env vars, binaries, or config paths).
Instruction Scope: okSKILL.md contains only informational content and a small read_when list indicating when to use the reference. It does not instruct the agent to read files, access system state, call external endpoints, or transmit data.
Install Mechanism: okNo install spec and no code files — the skill is instruction-only, so nothing is written to disk and no external packages are fetched.
Credentials: okThe skill requires no environment variables, credentials, or config paths; requested privileges are proportional (none) to its stated purpose.
Persistence & Privilege: okalways is false and model invocation is allowed (the platform default). The skill does not request persistent or elevated privileges and does not modify other skills or system settings.