技能 docx

📦

docx

Name: docx
Author: anthropics

内容修订 r1 安全 🌐 网络访问📁 文件系统访问⚙️ 外部命令

可靠地编辑 DOCX 文档

专业 Word 文档通常需要在不破坏格式的情况下进行精准编辑、添加批注和记录修订。此技能为 Claude、Codex 和 Claude Code 提供结构化的 DOCX 工作流，并配套 OOXML 工具和验证步骤。

支持: Claude Codex Code(CC)

📊 75 合格

使用我的智能体安装

将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。

智能体请求

Review the Skillstore skill "docx" from https://skillstore.io/skills/docx.md and its manifest at https://skillstore.io/api/skills/docx/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

你的智能体仍应展示其计划，并按安全策略请求必要确认。

Agent 可读资源

当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。

Markdown 详情 GET /skills/docx.md 已签名 manifest GET /api/skills/docx/manifest 已签名 lockfile GET /api/skills/docx/lockfile

测试它

正在使用“docx”。用户提供一份政策 DOCX，并要求生成一份审阅副本，其中包含针对模糊要求的批注。

预期结果:

一份修订后的 DOCX 文件，其中批注锚定到相关段落。
一份简短摘要，列出每条批注及其添加原因。
一条验证说明，确认文档已成功重新打包。

正在使用“docx”。用户要求根据 markdown 大纲和图表图像生成一份季度报告 DOCX。

预期结果:

一份格式化的 Word 文档，包含标题、章节、表格、图像和页面布局。
一份简短的构建摘要，说明包含的样式和插入的资源。

正在使用“docx”。用户请求对日期、当事方名称和付款条款进行带修订的合同编辑。

预期结果:

一份带红线修订的 DOCX 文件，包含精准的插入和删除。
一份按文档章节分组的已完成编辑清单。
一份基于转换后的 markdown 或验证输出的核验摘要。

安全审计

安全

v11 • 2026/7/9 打开版本化报告

The confirmed risks are expected for a DOCX manipulation skill: local file operations, ZIP package handling, temporary workspaces, subprocess calls, and privileged dependency installation guidance. Most static findings are false positives from OOXML namespace URIs, schema imports, Markdown code formatting, compact XML templates, or validation identifiers. No prompt injection attempt was found in the reviewed skill files. Static review was capped at 400/450 representative findings; omitted static matches are unconfirmed, so automatic publishing stays disabled until manual review.

已扫描文件

24,725

分析行数

复核项

已忽略误报

能力复核项 (48)

这些是真实的本地能力，对此技能可能是预期行为，因此需要复核，但不会按已确认恶意行为计分。

高

ooxml/scripts/unpack.py:17

Archive extract all (zip slip risk)

zipfile.ZipFile(input_file).extractall(output_path)

The script extracts Office ZIP contents from user-provided documents with extractall, which can write outside the target directory if entries contain traversal paths.

高

ooxml/scripts/validation/base.py:891

Archive extract all (zip slip risk)

zip_ref.extractall(temp_path)

The script extracts Office ZIP contents from user-provided documents with extractall, which can write outside the target directory if entries contain traversal paths.

高

ooxml/scripts/validation/docx.py:201

Archive extract all (zip slip risk)

zip_ref.extractall(temp_dir)

The script extracts Office ZIP contents from user-provided documents with extractall, which can write outside the target directory if entries contain traversal paths.

高

ooxml/scripts/validation/redlining.py:70

Archive extract all (zip slip risk)

zip_ref.extractall(temp_path)

The script extracts Office ZIP contents from user-provided documents with extractall, which can write outside the target directory if entries contain traversal paths.

高

ooxml/scripts/pack.py:103

Python subprocess.run

result = subprocess.run(

The helper invokes local external programs with subprocess.run for validation or diff generation.

高

ooxml/scripts/validation/redlining.py:153

Python subprocess.run

result = subprocess.run(

The helper invokes local external programs with subprocess.run for validation or diff generation.

高

ooxml/scripts/validation/redlining.py:185

Python subprocess.run

result = subprocess.run(

The helper invokes local external programs with subprocess.run for validation or diff generation.

高

SKILL.md:193

sudo privilege escalation

- **pandoc**: `sudo apt-get install pandoc` (for text extraction)

The skill documentation recommends sudo apt-get installation commands, which require elevated privileges.

高

SKILL.md:195

sudo privilege escalation

- **LibreOffice**: `sudo apt-get install libreoffice` (for PDF conversion)

The skill documentation recommends sudo apt-get installation commands, which require elevated privileges.

高

SKILL.md:196

sudo privilege escalation

- **Poppler**: `sudo apt-get install poppler-utils` (for pdftoppm to convert PDF to images)

The skill documentation recommends sudo apt-get installation commands, which require elevated privileges.

中

docx-js.md:20

Node.js fs operations

Packer.toBuffer(doc).then(buffer => fs.writeFileSync("doc.docx", buffer)); // Node.js

The docx-js workflow explicitly reads or writes local files when creating DOCX files or embedding images.

中

docx-js.md:265

Node.js fs operations

data: fs.readFileSync("image.png"),

The docx-js workflow explicitly reads or writes local files when creating DOCX files or embedding images.

中

ooxml/scripts/pack.py:15

Python archive libraries

import zipfile

The skill intentionally reads or writes DOCX package ZIP archives as part of document workflows.

中

ooxml/scripts/pack.py:76

Python archive libraries

with zipfile.ZipFile(output_file, "w", zipfile.ZIP_DEFLATED) as zf:

The skill intentionally reads or writes DOCX package ZIP archives as part of document workflows.

中

ooxml/scripts/unpack.py:7

Python archive libraries

import zipfile

The skill intentionally reads or writes DOCX package ZIP archives as part of document workflows.

中

ooxml/scripts/unpack.py:17

Python archive libraries

zipfile.ZipFile(input_file).extractall(output_path)

The skill intentionally reads or writes DOCX package ZIP archives as part of document workflows.

中

ooxml/scripts/validation/base.py:879

Python archive libraries

import zipfile

The skill intentionally reads or writes DOCX package ZIP archives as part of document workflows.

中

ooxml/scripts/validation/base.py:890

Python archive libraries

with zipfile.ZipFile(self.original_file, "r") as zip_ref:

The skill intentionally reads or writes DOCX package ZIP archives as part of document workflows.

中

ooxml/scripts/validation/docx.py:7

Python archive libraries

import zipfile

The skill intentionally reads or writes DOCX package ZIP archives as part of document workflows.

中

ooxml/scripts/validation/docx.py:200

Python archive libraries

with zipfile.ZipFile(self.original_file, "r") as zip_ref:

The skill intentionally reads or writes DOCX package ZIP archives as part of document workflows.

中

ooxml/scripts/validation/redlining.py:7

Python archive libraries

import zipfile

The skill intentionally reads or writes DOCX package ZIP archives as part of document workflows.

中

ooxml/scripts/validation/redlining.py:69

Python archive libraries

with zipfile.ZipFile(self.original_docx, "r") as zip_ref:

The skill intentionally reads or writes DOCX package ZIP archives as part of document workflows.

中

ooxml/scripts/pack.py:154

Python file write/append

with open(xml_file, "wb") as f:

The helper writes modified XML content back to files during packing.

中

ooxml.md:455

Python os file operations

os.makedirs(media_dir, exist_ok=True)

The documentation shows creating directories while modifying DOCX package contents.

中

ooxml.md:456

Python shutil operations

shutil.copy('image.png', os.path.join(media_dir, 'image1.png'))

The helper copies or removes document working directories as part of edit and save workflows.

中

ooxml/scripts/pack.py:67

Python shutil operations

shutil.copytree(input_dir, temp_content_dir)

The helper copies or removes document working directories as part of edit and save workflows.

中

scripts/document.py:642

Python shutil operations

shutil.copytree(self.original_path, self.unpacked_path)

The helper copies or removes document working directories as part of edit and save workflows.

中

scripts/document.py:836

Python shutil operations

shutil.rmtree(self.temp_dir)

The helper copies or removes document working directories as part of edit and save workflows.

中

scripts/document.py:884

Python shutil operations

shutil.copytree(self.unpacked_path, target_path, dirs_exist_ok=True)

The helper copies or removes document working directories as part of edit and save workflows.

中

scripts/document.py:958

Python shutil operations

shutil.copy(TEMPLATE_DIR / "people.xml", path)

The helper copies or removes document working directories as part of edit and save workflows.

中

scripts/document.py:1073

Python shutil operations

shutil.copy(TEMPLATE_DIR / "comments.xml", self.comments_path)

The helper copies or removes document working directories as part of edit and save workflows.

中

scripts/document.py:1094

Python shutil operations

shutil.copy(

The helper copies or removes document working directories as part of edit and save workflows.

中

scripts/document.py:1110

Python shutil operations

shutil.copy(TEMPLATE_DIR / "commentsIds.xml", self.comments_ids_path)

The helper copies or removes document working directories as part of edit and save workflows.

中

scripts/document.py:1121

Python shutil operations

shutil.copy(

The helper copies or removes document working directories as part of edit and save workflows.

中

docx-js.md:20

Synchronous file operations

Packer.toBuffer(doc).then(buffer => fs.writeFileSync("doc.docx", buffer)); // Node.js

The docx-js workflow reads or writes local files while creating DOCX output.

中

docx-js.md:265

Synchronous file operations

data: fs.readFileSync("image.png"),

The docx-js workflow reads or writes local files while creating DOCX output.

低

ooxml/scripts/pack.py:13

Temp file creation

import tempfile