Back to skill
Skillv1.0.0
ClawScan security
Reese · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 17, 2026, 1:10 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This skill is an instruction-only content provider about Reese's brand history and products; it requests no credentials, installs nothing, and its runtime instructions are limited to returning factual content, so its declared requirements and behavior are internally consistent.
- Guidance
- This skill is low-risk: it only contains static informational content about Reese's and asks for no credentials or installs. The only remaining consideration is provenance: the source/homepage is unknown, so if you need authoritative or citable references (dates, revenue figures, market shares), verify the facts against primary sources (Hershey reports, reputable industry articles). Otherwise it is safe to enable for informational queries.
Review Dimensions
- Purpose & Capability
- okName and description (Reese's brand history, products, seasonal market position) match the SKILL.md content. The skill declares no env vars, binaries, or config paths and doesn't request access to unrelated services — proportional to the stated purpose.
- Instruction Scope
- okSKILL.md contains only summary, context triggers, and static informational content (brand history, product list, market notes). It does not instruct the agent to run shell commands, read files, access environment variables, or transmit data to external endpoints beyond normal agent messaging.
- Install Mechanism
- okNo install spec and no code files are present (instruction-only). This is the lowest-risk pattern: nothing will be written to disk or fetched at install time.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths. There are no requests for secrets or unrelated service access, which is appropriate for a read-only informational skill.
- Persistence & Privilege
- okFlags: always=false (not force-included) and disable-model-invocation=false (normal — agent may call it autonomously). The skill does not request persistent presence or elevated privileges and does not modify other skills or system-wide settings.