←新闻详情

PromptArmor:Threat Intelligence更新于 10月14日 12:13

PromptArmor 推出 Claude 风险与配置用例工具

Claude Risks & Configs by Use Case | PromptArmor

AI 导读

PromptArmor 发布 Claude 风险与配置工具,用户可按用例开关功能,查看部署所需的管理员设置,右侧清单跟踪配置项及顺序。覆盖聊天与研究、法律、金融、编程等场景,涉及 Chat、Cowork、代码执行与文件创建、Skills 及数据与隐私控制等开关。

正文

当前显示原文,中文全文译文尚未就绪。

Pick a use case, toggle features on or off, and see exactly which admin settings your deployment needs. The checklist on the right tracks what to configure, and in what order.

Chat & research; Summarize documents; Draft & edit content; Analyze data & build reports; Automate with skills

Review & redline contracts; Legal research; Draft briefs & memos; Due diligence review; Privilege-aware controls

Build financial models; Analyze earnings & filings; Generate investor reports; Scenario analysis; Market research

Write & review code; Debug & explain errors; Generate tests; Run code in sandbox; Automate with Claude Code

Chat

Enable or disable the core Claude chat experience for your organization.

Cowork

Computer-use agent that can edit files, and run commands on the user's machine.

Code Execution & File Creation

Allow Claude to execute code in a sandbox and create/edit documents, spreadsheets, presentations, PDFs, and data reports.

Skills

Custom prompt-and-code bundles that extend Claude's capabilities. Skills can contain executable code and can be managed by admins or created by users.

Data & Privacy Controls

Controls for data sharing, feedback, and visibility within the organization.

来源

PromptArmor:Threat Intelligence