Back to skill
Skillv1.0.1
ClawScan security
思齐的三国演义读书笔记 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 10, 2026, 4:11 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is a simple, instruction-only reading-notes skill for 小学生 with no installs, no credentials, and no out-of-scope instructions — its requests match its stated purpose.
- Guidance
- This skill appears coherent and low-risk: it only contains instructions to produce chapter notes and questions and requests no credentials or installs. Before installing, consider: (1) review outputs for factual accuracy and age-appropriateness (LLMs can hallucinate or simplify incorrectly); (2) if you expect the skill to quote long passages, verify copyright constraints (this particular book is typically public-domain, but checking is prudent); and (3) it can be invoked autonomously by the agent by default — if you prefer manual control, disable autonomous invocation in your agent settings.
Review Dimensions
- Purpose & Capability
- okName/description (chapter-by-chapter notes, prompts for reflections and character summaries) align with the content of SKILL.md. The skill does not request unrelated resources (no env vars, no binaries).
- Instruction Scope
- okSKILL.md only instructs the agent to generate chapter outlines, writing ideas, and questions for reflection. It does not ask the agent to read files, access system state, call external endpoints, or exfiltrate data.
- Install Mechanism
- okNo install spec and no code files — instruction-only. This minimizes disk writes and external installation risk.
- Credentials
- okThe skill requires no environment variables, credentials, or config paths, which is appropriate for its described functionality.
- Persistence & Privilege
- okalways is false and the skill is user-invocable; autonomous model invocation is enabled by default but is not combined with elevated privileges or broad access in this skill.