Doc Handler - 文档处理

读取和编辑 Word、PDF、Excel 文档。使用 python-docx、pdfplumber、openpyxl

Security Scan

The skill largely does what it claims (read Word/PDF/Excel) but the documentation advertises a write command that is not implemented in the included code — this mismatch and a few documentation oddities make the package suspicious rather than clearly benign.

Purpose & Capability

Name/description match the code's primary functionality: reading .docx, .pdf, and .xlsx files. Declared dependencies (python-docx, pdfplumber, openpyxl, pandas) align with those capabilities. However SKILL.md claims a 'write docx' command that the provided code does not implement, which is an incoherence between advertised capability and delivered code.

Instruction Scope

SKILL.md instructs running the module to read and (per the command table) write documents, but doc_handler.py only implements reading and a simple CLI for 'read'. Examples in SKILL.md also show ad-hoc python -c snippets (which are fine) but the presence of an advertised write command that has no implementation is misleading. The runtime instructions do not reference network calls or extra env vars; they do, however, instruct reading arbitrary files supplied to the tool — these files can contain sensitive data, so callers should be careful about where output goes.

Install Mechanism

No install specification is provided and this is an instruction- + single-file code skill. Nothing is downloaded or installed automatically by the skill itself, which reduces install-time risk. The user will need to install the declared Python packages manually or in their environment.

Credentials

No environment variables, credentials, or config paths are requested. That is proportional to the stated purpose. The skill reads local files only and does not request unrelated secrets.

Persistence & Privilege

always is false and the skill does not request persistent presence or modify other skills/configuration. It runs only when invoked and does not request elevated platform privileges.

What to consider before installing

This package appears to be a simple document reader, but the SKILL.md advertises a 'write' command that the included script does not implement — likely a documentation/code mismatch. Before installing or enabling: (1) review and test the provided doc_handler.py locally in a sandbox, (2) install the listed Python packages (python-docx, pdfplumber, openpyxl, pandas) in a controlled environment, (3) do not pass sensitive files to the skill unless you trust where its output will go (the tool prints file contents to stdout which could be forwarded by the agent), and (4) if you need write functionality, request the author/publisher for a corrected implementation or add/verify the write logic yourself. The mismatch suggests sloppy packaging rather than obvious malicious intent, but exercise caution and avoid granting the agent access to private files until you're comfortable with the code.

doc-handler - 文档处理工具

功能

功能	命令
读取 Word	python3 -m doc_handler read docx 文件
读取 PDF	python3 -m doc_handler read pdf 文件
读取 Excel	python3 -m doc_handler read xlsx 文件
写入 Word	python3 -m doc_handler write docx 文件 "内容"

使用示例

# 读取 Word 文档
python3 -c "from docx import Document; d = Document('file.docx'); print('\\n'.join([p.text for p in d.paragraphs]))"

# 读取 PDF
python3 -c "import pdfplumber; with pdfplumber.open('file.pdf') as pdf: print(pdf.pages[0].extract_text())"

# 读取 Excel
python3 -c "import pandas; df = pandas.read_excel('file.xlsx'); print(df)"

依赖

• python-docx
• pdfplumber
• openpyxl
• pandas