Back to skill
Skillv1.0.0
ClawScan security
Patek Philippe · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 16, 2026, 7:47 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only, content-focused skill that provides a Patek Philippe brand guide; its requested footprint and runtime instructions are consistent with that purpose.
- Guidance
- This skill is an instruction-only content guide about Patek Philippe and appears internally consistent and low-risk. Before installing, consider: (1) the content may become outdated or contain minor factual errors — verify important facts against authoritative sources; (2) it has no code or external integrations, so it won’t access your system or secrets; (3) autonomous invocation is allowed by default on the platform — if you prefer, adjust agent settings to require explicit user invocation.
Review Dimensions
- Purpose & Capability
- okThe skill's name, description, and SKILL.md all describe a brand guide for Patek Philippe. There are no extra binaries, env vars, or config paths required — nothing requested that is unrelated to providing informational content.
- Instruction Scope
- okSKILL.md contains only static guidance and trigger conditions (read_when). It does not instruct the agent to read arbitrary system files, access environment variables, call external endpoints, or exfiltrate data.
- Install Mechanism
- okNo install spec and no code files are present (instruction-only). That minimizes disk writes and code-execution risk.
- Credentials
- okThe skill declares no environment variables, credentials, or config paths. It does not request secrets or access to unrelated services.
- Persistence & Privilege
- okDefaults are used (not always:true). The skill is user-invocable and can be called autonomously per platform defaults, which is expected for a normal skill and not excessive here.