Back to skill
Skillv1.0.0
ClawScan security
Qzone · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 16, 2026, 9:20 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only QQ空间运营 assistant whose content and requirements are consistent with its stated purpose and it does not request credentials, install software, or access system resources.
- Guidance
- This skill is instruction-only and coherent with its stated purpose. Before installing or using it: do not provide login credentials, tokens, or passwords to the skill; confirm you trust the source (owner is unknown); periodically review updates in case future versions add integrations that request tokens or external access; if any later version asks for API keys or accesses files, treat that as a red flag and revoke access.
Review Dimensions
- Purpose & Capability
- okThe name/description (QQ空间运营助手) matches the SKILL.md content: content creation, album management, interaction and basic audience/ distribution guidance. The skill does not request unrelated privileges or tooling.
- Instruction Scope
- okSKILL.md contains only editorial and operational guidance (posting tips, album organization, interaction strategies, permissions advice). It does not instruct reading files, environment variables, system paths, or sending data to external endpoints.
- Install Mechanism
- okNo install spec or code files are present; this is instruction-only and will not write or execute code on disk.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. Nothing in the instructions asks for secrets or external API keys.
- Persistence & Privilege
- okalways is false and the skill does not request persistent system presence or modify other skill/system settings. It is user-invocable and can be called by the agent (normal behavior).