Back to skill
Skillv1.0.0
ClawScan security
Tag Heuer · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 17, 2026, 8:57 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only skill that provides a Tag Heuer brand guide; it requests no credentials, performs no installs, and its runtime instructions stay within the described purpose.
- Guidance
- This skill appears low-risk: it only supplies brand background and asks for nothing else. Before installing, consider that the source and homepage are not provided (provenance is unknown) — if you need authoritative or up-to-date facts (dates, revenue, partnership status) verify against official TAG Heuer or LVMH sources. Because it is instruction-only and requests no credentials, there is minimal privacy/security exposure. If you have stricter policies, prefer skills with a verifiable homepage or known publisher.
Review Dimensions
- Purpose & Capability
- okName/description (Tag Heuer brand guide) matches the SKILL.md content. The skill requires no binaries, env vars, or config paths — consistent with an information/reference skill.
- Instruction Scope
- okSKILL.md contains only brand information and a 'read_when' trigger list for when to present that information. It does not instruct the agent to read local files, environment variables, or contact external endpoints beyond serving brand content.
- Install Mechanism
- okNo install spec or code files are present (instruction-only), so there is nothing written to disk or downloaded during installation.
- Credentials
- okNo environment variables, credentials, or config paths are requested. The skill does not ask for any secrets or unrelated access.
- Persistence & Privilege
- okalways is false (default) and model invocation is allowed (default). Those defaults are normal for a user-invocable informational skill and are not combined with any broad privileges or credential access.