article-taster

文章品鉴师 - 多维度评估文章质量、检测AI味/大便味、识别原创内容

This skill appears internally coherent for the stated purpose (article quality scoring and AI-detection) and contains only local Python code and configuration. However, because the package includes executable Python scripts, treat it like any third‑party code before running: 1) review the source (you have it) for any hidden network calls or unexpected file/system access; 2) install and run it in an isolated environment (virtualenv, container, or sandbox) and avoid running it on systems with sensitive data; 3) do not feed highly sensitive documents into the tool until you are comfortable with its behavior; 4) install dependencies (requirements.txt) only in the sandbox; 5) be aware the AI-detection is heuristic-based and can misclassify content (the code even includes exemption rules for poetry/classics). If you need higher assurance, run static analysis tools or have a developer audit the code for any subtle data exfiltration or OS-level operations before using it on production machines.

Type: OpenClaw Skill Name: tmpz3kwrq8c Version: 1.0.0 The 'article-taster' skill bundle is a legitimate tool designed to analyze article quality and detect AI-generated content using heuristic-based NLP techniques. The code implements various analyzers (technical, creative, novel) that calculate scores based on word density, sentence structure, and specific keywords, with no evidence of data exfiltration, unauthorized network access, or malicious execution. All scripts (e.g., main.py, ai_detector.py) align strictly with the stated purpose of providing reading recommendations and quality reports.