Back to skill
Skillv1.0.0
ClawScan security
爆款标题生成器技能 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 18, 2026, 8:29 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is instruction-only and its declared behavior, required files, and resource access are consistent with a headline/title-generation tool.
- Guidance
- This skill appears coherent and does not request credentials or install anything. Before installing: (1) be aware it will generate titles immediately without asking clarifying questions—provide clear context for best results; (2) review generated titles for honesty and policy compliance (avoid misleading/clickbait claims that violate platform rules); (3) do not send sensitive personal or account data to the skill when prompting, though the skill itself does not attempt to access secrets or external endpoints.
Review Dimensions
- Purpose & Capability
- okName/description (爆款标题生成器) match the SKILL.md and the included formula reference. It requests no external credentials, binaries, or installs that would be unrelated to generating platform-style titles.
- Instruction Scope
- noteRuntime instructions are limited to parsing user input, selecting formulas from the included references file, generating 5 styled titles, estimating CTR, and giving publishing suggestions. The SKILL.md enforces immediate output without follow-up questions, which is a design choice (not a security issue) but can reduce quality if the user's prompt is ambiguous.
- Install Mechanism
- okNo install spec and no code files beyond SKILL.md and a local reference; nothing will be downloaded or written to disk by an installer. This is the lowest-risk installation model.
- Credentials
- okNo environment variables, credentials, or config paths are required. The skill does not attempt to access external endpoints or secrets, and all referenced content is included in the package.
- Persistence & Privilege
- okalways:false (default) and user-invocable. The skill does not request or imply elevated or persistent system privileges and does not modify other skills or system config.