Back to skill
Skillv1.0.0
ClawScan security
Ben & Jerry's · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 9:11 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This skill is an instruction-only informational card about Ben & Jerry's; it requests no credentials, installs nothing, and its content matches its stated purpose.
- Guidance
- This skill is low-risk: it's a local, read-only content card about Ben & Jerry's and requires no installs or credentials. Before relying on its facts, verify any critical numbers or historical claims against authoritative sources (official company pages, news reports) because SKILL.md content may be out of date or incomplete. If you need sourcing or citations, request them from the skill author or prefer skills that link to primary sources.
Review Dimensions
- Purpose & Capability
- okName/description claim an informational brand overview; the SKILL.md provides exactly that (history, business model, facts). There are no unrelated requirements (no env vars, binaries, or config paths).
- Instruction Scope
- okSKILL.md is a static reference card and its 'read_when' triggers are limited to discussion contexts (CSR, acquisitions, ice cream industry). It does not instruct the agent to read files, call external endpoints, or collect unrelated data.
- Install Mechanism
- okNo install spec is included (instruction-only). Nothing is downloaded or written to disk.
- Credentials
- okNo environment variables or credentials are requested, which is appropriate for a read-only informational skill.
- Persistence & Privilege
- okSkill is not always-enabled and allows normal agent invocation rules. It does not request elevated persistence or modify other skills/configuration.