Back to skill
Skillv1.0.0
ClawScan security
Abbott Labs · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 28, 2026, 4:07 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is a read-only, informational skill summarizing Abbott Laboratories; it requests no credentials, makes no installs, and its instructions are limited to content for researcher prompts.
- Guidance
- This skill is informational and low-risk: it only contains a company summary in Chinese and asks for no access to your system or secrets. Because the publisher/source is unknown, verify facts against trusted sources before relying on this for decisions (especially medical or regulatory). If you need authoritative or up-to-date data (financials, recall details, clinical guidance), consult official Abbott publications or primary sources.
Review Dimensions
- Purpose & Capability
- okThe name and description (Abbott Labs company overview) match the SKILL.md content. The skill does not request unrelated binaries, environment variables, or config paths — its declared purpose aligns with what it contains.
- Instruction Scope
- okSKILL.md is purely an informational document with 'read_when' contexts for research scenarios. It does not instruct the agent to read local files, access environment variables, call external endpoints, or transmit data.
- Install Mechanism
- okNo install spec or code files beyond the SKILL.md. Being instruction-only, nothing is written to disk or downloaded during install.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths and the instructions do not reference any secrets or system config.
- Persistence & Privilege
- okDefault invocation settings (always: false, disable-model-invocation: false) are appropriate for a user-invocable informational skill; it does not request permanent presence or modify other skills.