Back to skill
Skillv1.0.0
ClawScan security
朋友圈文案生成器 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 2:32 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only Chinese "朋友圈文案生成器" skill whose declared purpose (generating social post copy) matches its instructions and it requests no installs, binaries, or credentials.
- Guidance
- This skill appears internally consistent and low-risk because it is instruction-only and requires no credentials or installs. Before using: (1) test outputs for accuracy and tone, (2) ensure generated promotional content complies with local laws and platform rules (e.g., advertising disclosure), and (3) watch for future versions that add external network calls, install scripts, or request API keys/config paths—those would be a red flag.
Review Dimensions
- Purpose & Capability
- okName/description match the SKILL.md: the skill is a copywriter for social posts and the instructions only describe generating multi-style copy, emojis, timing, image and interaction suggestions. No unrelated capabilities or credentials are requested.
- Instruction Scope
- okSKILL.md contains only content/format guidance for generating posts (styles, scenarios, output fields). It does not instruct the agent to read files, access environment variables, call external endpoints, or exfiltrate data.
- Install Mechanism
- okNo install spec or code files are present; this is instruction-only so nothing is written to disk or installed during setup.
- Credentials
- okNo environment variables, credentials, or config paths are required. The requested scope is proportional to a text-generation helper.
- Persistence & Privilege
- okSkill is not forced-always and uses default invocation settings. It does not request persistent or system-wide privileges.