PDF QR Extractor

Extracts and saves QR codes from each page of a PDF by converting pages to images and detecting QR regions with padding.

Security Scan

The skill's code, instructions, and requirements are consistent with its stated purpose of extracting QR images from PDFs; it runs locally, requests no secrets, and does not contact external endpoints.

Purpose & Capability

Name/description, SKILL.md, README, and the included script all describe PDF->image conversion and QR detection using PyMuPDF (fitz), OpenCV and pyzbar. Required capabilities and files align with the stated purpose; no unrelated credentials or system accesses are requested.

Instruction Scope

Runtime instructions are narrowly scoped: convert PDF pages to images, detect/crop QR regions, add padding, and save files to an output directory. The SKILL.md and script only read the provided PDF and write image files; they do not attempt to read other system files, environment variables, or send data externally.

Install Mechanism

This is an instruction-only skill (no automated install). SKILL.md asks the user to pip install fitz PyMuPDF opencv-python numpy pyzbar. That is expected, but note: (1) pyzbar typically requires a system zbar library (native dependency) which is not mentioned; (2) listing both "fitz" and "PyMuPDF" is redundant/confusing (PyMuPDF provides the fitz module); (3) the pip suggestion includes --break-system-packages, which alters system package isolation and should be used cautiously. These are installation/usability notes rather than indicators of malicious behavior.

Credentials

The skill requests no environment variables or credentials. The script only reads the provided PDF path and writes output files; requested access is proportional to the functionality.

Persistence & Privilege

always is false and the skill does not request persistent or elevated platform privileges, nor does it modify other skills or global agent settings.

Assessment

This skill appears to do what it says and runs locally. Before installing/running: (1) review and run the included script on non-sensitive test PDFs; (2) install Python dependencies in an isolated virtual environment (avoid --break-system-packages unless you understand its effect); (3) ensure the system zbar library is installed for pyzbar to work; (4) be mindful that the script will write image files to disk (ensure output path permissions are appropriate). If you need stricter isolation, run it inside a disposable VM or container.

PDF QR Code Extractor

从 PDF 文件中提取每一页的图片，并检测、裁剪保存其中的二维码。

功能

• 将 PDF 每一页转换为图片
• 使用 OpenCV + pyzbar 检测并裁剪二维码区域
• 二维码周围留有 10 像素白边（padding），便于扫码识别
• 保存到指定目录

使用方法

请帮我提取 PDF 中的二维码：[PDF文件路径]

例如：

请帮我提取 PDF 中的二维码：D:/pdftest/text.pdf

或者指定输出目录：

请帮我提取 PDF 中的二维码：D:/pdftest/text.pdf，输出到 ./my_qr

依赖安装

需要先安装依赖：

pip install fitz PyMuPDF opencv-python numpy pyzbar --break-system-packages

输出结构

输出目录/
├── qr_page_1_1.png      # 二维码图片
├── qr_page_2_1.png
├── text.pdf_pages/       # PDF页面图片（中间文件）
│   ├── page_1.png
│   └── page_2.png

适用场景

客户提供的 PDF 文件中包含生成的二维码，需要批量提取保存。