Back to skill
Skillv1.0.0
ClawScan security
Sinopec · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 17, 2026, 3:26 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only skill that provides a written brand/profile summary of Sinopec and does not request credentials, install software, or access system files.
- Guidance
- This skill appears to be a safe, content-only helper for producing a Sinopec brand/profile summary. It does not request access to credentials or install software. Keep in mind: the skill's outputs depend on the model's knowledge and any external sources the agent uses; verify facts (especially financial, legal, or operational details) against official Sinopec channels or recent reputable sources before making critical decisions.
Review Dimensions
- Purpose & Capability
- okThe name and description promise a brand profile and the SKILL.md contains only guidance for producing that content. There are no unrelated requirements (no env vars, binaries, or config paths).
- Instruction Scope
- okSKILL.md is limited to describing the kind of company information to provide (history, products, market presence). It does not instruct the agent to read files, call external endpoints, or access credentials.
- Install Mechanism
- okNo install spec or code is provided (instruction-only), so nothing is written to disk or fetched at install time.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths — proportional to a content-only documentation/helper skill.
- Persistence & Privilege
- okalways is false and the skill does not request elevated or persistent privileges. It is user-invocable and may be called by the agent when relevant (normal behavior).