Back to skill
Skillv1.0.0
ClawScan security
Cartier Jewelry · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 8:04 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only informational skill about Cartier (brand history, business, product lines) and its declared requirements and instructions are consistent with that purpose.
- Guidance
- This skill appears to be a harmless, read-only informational piece about Cartier. Before installing, note that the skill has no listed source or homepage—if provenance matters to you, prefer skills with identified authors or official sources. Also consider your agent's network and browsing permissions: if you do not want the agent to perform live web research when invoked, restrict network access or model invocation accordingly. No credentials or system access are requested by this skill.
Review Dimensions
- Purpose & Capability
- okThe name and description (Cartier jewelry/brand profile) match the SKILL.md content and the 'read_when' research prompts. Nothing requested (no env vars, no binaries, no installs) is out of scope for a research/informational skill.
- Instruction Scope
- okSKILL.md contains research prompts and static brand content (history, business model, data, trivia). It does not instruct the agent to read arbitrary local files, access unrelated credentials, or transmit data to unexpected endpoints.
- Install Mechanism
- okNo install spec and no code files are present. Being instruction-only means nothing is written to disk or installed by the skill.
- Credentials
- okThe skill requests no environment variables or credentials; there is no disproportionate credential or config access.
- Persistence & Privilege
- okThe skill is not marked always:true and does not request persistent system privileges or to modify other skills. It can be invoked by the agent (default behavior) which is appropriate for an informational skill.