Back to skill
Skillv1.0.0
ClawScan security
Farfetch Luxury · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 28, 2026, 9:04 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only, read-only informational skill about Farfetch whose declared purpose matches its content and which requests no permissions or installs.
- Guidance
- This skill is low-risk because it only contains static explanatory text and requests no credentials or installs. Before installing, consider: (1) the source is unknown — verify facts (e.g., the claimed 2024 Coupang acquisition and numeric figures) against primary sources if you rely on them; (2) prefer skills from identifiable authors or official repositories when provenance matters; and (3) if a future version adds installs, env vars, or external network calls, re-evaluate because that would increase risk.
Review Dimensions
- Purpose & Capability
- okThe name and description describe an informational briefing on Farfetch; the SKILL.md provides that information and requires no additional capabilities or credentials.
- Instruction Scope
- okSKILL.md is static, domain-focused content and 'read_when' triggers; it does not instruct the agent to run commands, read files, access environment variables, or send data to external endpoints.
- Install Mechanism
- okNo install spec or code files are present (instruction-only), so nothing will be written to disk or downloaded during installation.
- Credentials
- okNo environment variables, credentials, or config paths are requested — proportional to an informational skill.
- Persistence & Privilege
- okalways is false and the skill does not request system or cross-skill configuration changes; autonomous invocation is allowed but is the platform default and not excessive here.