跳转到正文
skillsafebeta
← 报告库
用途分类 / 文档处理

Doc Coauthoring Skill 安全审计

作者说它能做什么（原文）

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or

第三方安全检查结论

发现安全风险

已检查文件
1
发现的风险
4
会不会运行危险命令？检查是否下载程序后直接运行、让他人远程控制电脑，或藏起要运行的命令。未发现风险
会不会泄露文件和密钥？检查是否发送含密码或密钥的文件，以及代码里是否直接写了密钥。发现 4 项风险
中风险

鼓励收集范围宽泛的内部组织信息

原文依据：3 处
发现了什么

流程明确索取团队动态、历史事件、内部政治、讨论线程及共享文档，并建议通过连接器直接读取。虽然这些信息可能帮助写作，但可能远超文档必要范围；提到频道或文档后，流程只要求通知用户即开始读取，而不是逐项确认范围。

为什么需要注意

启用连接器时，私密讨论、人员关系、事件记录或无关文档内容可能被带入模型上下文和草稿，扩大敏感信息的处理与意外传播范围。

该流程主动鼓励用户提供团队动态、过往事件、内部政治、讨论频道和共享文档，并在集成可用时直接读取。对未知实体的搜索要求确认，但对用户已提到的频道或文档只要求先通知再读取，未要求逐项限定范围。若相关来源含与成稿无关的机密或个人信息，会扩大暴露面；用户可要求仅提供成稿必需资料，并逐个批准来源和范围。

SKILL.md:56来自说明文档打开原文件
Once initial questions are answered, encourage the user to dump all the context they have. Request information such as:- Background on the project/problem- Related team discussions or shared documents- Why alternative solutions aren't being used- Organizational context (team dynamics, past incidents, politics)- Timeline pressures or constraints- Technical architecture or dependencies- Stakeholder concernsAdvise them not to worry about organizing it - just get it all out. Offer multiple ways to provide context:- Info dump stream-of-consciousness- Point to team channels or threads to read- Link to shared documents**If integrations are available** (e.g., Slack, Teams, Google Drive, SharePoint, or other MCP servers), mention that these can be used to pull in context directly.
查看另外 2 个位置
SKILL.md:76来自说明文档打开原文件
**During context gathering:**- If user mentions team channels or shared documents:  - If integrations available: Inform them the content will be read now, then use the appropriate integration  - If integrations not available: Explain lack of access. Suggest they enable connectors in Claude settings, or paste the relevant content directly.- If user mentions entities/projects that are unknown:  - Ask if connected tools should be searched to learn more  - Wait for user confirmation before searching
SKILL.md:65来自说明文档打开原文件
Advise them not to worry about organizing it - just get it all out. Offer multiple ways to provide context:- Info dump stream-of-consciousness- Point to team channels or threads to read- Link to shared documents**If integrations are available** (e.g., Slack, Teams, Google Drive, SharePoint, or other MCP servers), mention that these can be used to pull in context directly.
中风险

读者测试会把完整文档交给新的模型会话或子代理

原文依据：3 处
发现了什么

自动路径会为每个问题把文档内容交给新的子代理；手动路径要求用户在 Claude.ai 新会话中粘贴文档或分享连接器链接。流程没有先检查文档的保密等级，也没有要求最小化或脱敏。

为什么需要注意

技术规格、未发布计划、客户资料、凭据或受监管信息可能被发送到用户原本未批准的额外处理上下文。共享文档链接还可能扩大连接器可访问的内容。

自动测试明确把文档内容与问题交给新的子代理；无子代理时则让用户把文档粘贴到新的 Claude.ai 会话，或通过连接器分享链接。可见流程未在这些步骤中要求检查保密等级、脱敏或只传递必要片段。若文档含机密信息，这会扩大其处理范围；用户可要求本地测试、最小片段测试或先脱敏。

SKILL.md:261来自说明文档打开原文件
### Step 2: Test with Sub-AgentAnnounce that these questions will be tested with a fresh Claude instance (no context from this conversation).For each question, invoke a sub-agent with just the document content and the question.Summarize what Reader Claude got right/wrong for each question.
查看另外 2 个位置
SKILL.md:300来自说明文档打开原文件
### Step 2: Setup TestingProvide testing instructions:1. Open a fresh Claude conversation: https://claude.ai2. Paste or share the document content (if using a shared doc platform with connectors enabled, provide the link)3. Ask Reader Claude the generated questions
SKILL.md:290来自说明文档打开原文件
**If no access to sub-agents (e.g., claude.ai web interface):**The user will need to do the testing manually.### Step 1: Predict Reader QuestionsAsk what questions people might ask when trying to discover this document. What would they type into Claude.ai?Generate 5-10 questions that readers would realistically ask.### Step 2: Setup TestingProvide testing instructions:1. Open a fresh Claude conversation: https://claude.ai2. Paste or share the document content (if using a shared doc platform with connectors enabled, provide the link)3. Ask Reader Claude the generated questions
中风险

建议在附录链接完整协作对话，可能泄露未进入成稿的内容

原文依据：2 处
发现了什么

最终提示建议把本次对话链接放入附录。协作对话可能包含被删除的方案、内部政治、历史事件、个人意见以及连接器取回的资料，这些内容不一定适合文档读者。

为什么需要注意

一旦文档被分享，读者可能借该链接看到比最终成稿更敏感、更宽泛的信息，并可能扩大到不应接触这些背景的人员。

最终建议把协作对话链接放进文档附录，而前面的流程鼓励对话包含内部政治、历史事件和其他原始背景。该建议是可选的，但没有要求先审阅访问权限或删去未进入成稿的敏感内容。若文档被广泛共享，附录链接可能让读者看到更大范围的对话；用户可拒绝链接，或仅附经过审阅和脱敏的摘要。

SKILL.md:344来自说明文档打开原文件
**If user wants final review, provide it. Otherwise:**Announce document completion. Provide a few final tips:- Consider linking this conversation in an appendix so readers can see how the doc was developed- Use appendices to provide depth without bloating the main doc- Update the doc as feedback is received from real readers
查看另外 1 个位置
SKILL.md:56来自说明文档打开原文件
Once initial questions are answered, encourage the user to dump all the context they have. Request information such as:- Background on the project/problem- Related team discussions or shared documents- Why alternative solutions aren't being used- Organizational context (team dynamics, past incidents, politics)- Timeline pressures or constraints- Technical architecture or dependencies- Stakeholder concerns
中风险

关于图片可见性的笼统断言可能诱导用户上传敏感图片

原文依据：1 处
发现了什么

流程断言没有替代文字时 Claude 无法看到图片，并因此要求用户把每张图片粘贴进聊天。实际可见性取决于平台和工具；该绝对说法没有先检查图片敏感性或解释上传后的处理范围。

为什么需要注意

用户可能上传架构图、截图、客户资料或包含密钥的图片，即使只需本地添加替代文字，从而产生不必要的数据披露。

流程要求先询问用户是否需要替代文字，因此上传并非强制；但它笼统声称 Claude 无法看到缺少替代文字的图片，并在用户同意后要求把每张图片粘贴到聊天中。若图片含凭据、个人信息或内部界面，这会把内容带入聊天处理范围，且该步骤未提示先检查或遮盖敏感部分。用户可只提供文字描述，或先裁剪、打码。

SKILL.md:49来自说明文档打开原文件
**If user mentions editing an existing shared document:**- Use the appropriate integration to read the current state- Check for images without alt-text- If images exist without alt-text, explain that when others use Claude to understand the doc, Claude won't be able to see them. Ask if they want alt-text generated. If so, request they paste each image into chat for descriptive alt-text generation.
会不会删除文件或一直在后台运行？检查是否大范围删除文件、改写磁盘，或设置自动启动。未发现风险
会不会绕过安全保护？检查是否跳过网站安全验证、开放过多文件权限，或取消操作前的确认。未发现风险
会不会误导 AI 或隐藏内容？检查工作说明是否要求 AI 忽略你的指令、干扰检查结果，或夹带看不见的文字。未发现风险
会不会偷偷改推广链接或收款方？检查是否强制替换推广链接或收款对象，同时要求隐瞒更改。未发现风险

Skill 逻辑拆解

6 个说明模块

该 Skill 是一个三阶段文档协作流程：收集上下文、逐节起草与修改、再用独立读者视角测试。

查看原文
SKILL.md:8来自说明文档打开原文件
This skill provides a structured workflow for guiding users through collaborative document creation. Act as an active guide, walking users through three stages: Context Gathering, Refinement & Structure, and Reader Testing.

上下文收集可能读取用户指定的团队频道和共享文档；对于未知实体，流程要求先取得用户确认再搜索连接的工具。

查看原文
SKILL.md:76来自说明文档打开原文件
**During context gathering:**- If user mentions team channels or shared documents:  - If integrations available: Inform them the content will be read now, then use the appropriate integration  - If integrations not available: Explain lack of access. Suggest they enable connectors in Claude settings, or paste the relevant content directly.- If user mentions entities/projects that are unknown:  - Ask if connected tools should be searched to learn more  - Wait for user confirmation before searching

结构确定后，该 Skill 会创建带占位符的文档；没有 artifact 功能时，会在工作目录创建 Markdown 文件，并在后续迭代中直接修改它。

查看原文
SKILL.md:130来自说明文档打开原文件
**Once structure is agreed:**Create the initial document structure with placeholder text for all sections.**If access to artifacts is available:**Use `create_file` to create an artifact. This gives both Claude and the user a scaffold to work from.Inform them that the initial structure with placeholders for all sections will be created.Create artifact with all section headers and brief placeholder text like "[To be written]" or "[Content here]".Provide the scaffold link and indicate it's time to fill in each section.**If no access to artifacts:**Create a markdown file in the working directory. Name it appropriately (e.g., `decision-doc.md`, `technical-spec.md`).Inform them that the initial structure with placeholders for all sections will be created.Create file with all section headers and placeholder text.Confirm the filename has been created and indicate it's time to fill in each section.

读者测试有两种路径：可用子代理时，将文档内容和问题交给新的代理；不可用时，要求用户在新的 Claude.ai 会话中粘贴或共享文档。

查看原文
SKILL.md:261来自说明文档打开原文件
### Step 2: Test with Sub-AgentAnnounce that these questions will be tested with a fresh Claude instance (no context from this conversation).For each question, invoke a sub-agent with just the document content and the question.Summarize what Reader Claude got right/wrong for each question.
SKILL.md:300来自说明文档打开原文件
### Step 2: Setup TestingProvide testing instructions:1. Open a fresh Claude conversation: https://claude.ai2. Paste or share the document content (if using a shared doc platform with connectors enabled, provide the link)3. Ask Reader Claude the generated questions
从这里开始 · 工作说明SKILL.md
doc-coauthoring
连线表示工作说明包含的模块，不是实际运行顺序。点击模块可查看原文。
文件与检查记录1 个文件

检查范围与遗漏

逐文件查看涉及的内容

下方列出本次涉及的原文范围；纳入检查不代表已查清所有问题。

  • SKILL.md已纳入全文

这份报告只针对上方版本。我们看了拿到的代码和说明文件，没有实际运行 Skill，也没有检查它另外安装的软件包。因此，这不是“保证安全”的承诺；换了版本或使用环境，结果也可能不同。

  • SKILL.md工作说明

代码和说明中提到的操作

连接外部网站
SKILL.md:303来自说明文档打开原文件
Provide testing instructions:1. Open a fresh Claude conversation: https://claude.ai2. Paste or share the document content (if using a shared doc platform with connectors enabled, provide the link)
读取了多少行
376
文件校验值（用于核对版本）
10aad9b41e16a7db568aca2ac80f517b6ba66478f01be890e305aaa3b2b2dda4