Back to Details

azure-content-safety

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Azure AI Content Safety Skill

Azure AI Content Safety Skill

This skill provides expert guidance for Azure AI Content Safety. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
本Skill提供Azure AI Content Safety的专业指导，涵盖故障排查、最佳实践、决策制定、架构与设计模式、限制与配额、安全、配置和部署。它结合了本地快速参考内容与远程文档获取功能。

How to Use This Skill

如何使用本Skill

IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g., 
L35-L120
), use 
read_file
with the specified lines. For categories with file links (e.g., 
[security.md](security.md)
), use 
read_file
on the linked reference file
IMPORTANT for Agent: If 
metadata.generated_at
is more than 3 months old, suggest the user pull the latest version from the repository. If 
mcp_microsoftdocs
tools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
  • Preferred: Use 
    mcp_microsoftdocs:microsoft_docs_fetch
    with query string 
    from=learn-agent-skill
    . Returns Markdown.
  • Fallback: Use 
    fetch_webpage
    with query string 
    from=learn-agent-skill&accept=text/markdown
    . Returns Markdown.
Agent 重要提示：使用下方的分类索引查找相关章节。对于带有行范围的分类（如
L35-L120
），使用
read_file
工具读取指定行内容。对于带有文件链接的分类（如
[security.md](security.md)
），使用
read_file
工具读取链接的参考文件
Agent 重要提示：如果
metadata.generated_at
已超过3个月，建议用户从仓库拉取最新版本。如果
mcp_microsoftdocs
工具不可用，建议用户安装：安装指南
本Skill需要网络访问权限以获取文档内容：
  • 首选方式：使用
    mcp_microsoftdocs:microsoft_docs_fetch
    工具，查询字符串为
    from=learn-agent-skill
    ，返回Markdown格式内容。
  • 备用方式：使用
    fetch_webpage
    工具，查询字符串为
    from=learn-agent-skill&accept=text/markdown
    ，返回Markdown格式内容。

Category Index

分类索引

CategoryLinesDescription
TroubleshootingL36-L40Diagnosing and resolving Azure AI Content Safety API errors, including HTTP status codes, common failure causes, and recommended fixes or retries.
Best PracticesL41-L45Tuning Content Safety thresholds, categories, and prompts to reduce misclassifications, plus strategies to balance safety, recall, and user experience.
Decision MakingL46-L51Guidance on migrating apps from Content Safety preview to GA and deciding when and how to use limited-access Content Safety features and models.
Architecture & Design PatternsL52-L56Architectural guidance for combining cloud, hybrid, and on-device Azure AI Content Safety, including design patterns, deployment options, and integration strategies.
Limits & QuotasL57-L63Language coverage, building and training custom safety categories, and detecting protected/third‑party code in model outputs.
SecurityL64-L68Details on how Azure AI Content Safety encrypts data at rest, including encryption models, key management options, and compliance/security considerations.
ConfigurationL69-L73Configuring and using text blocklists in Azure AI Content Safety, including creating, managing, and applying custom blocked terms to filter harmful or unwanted content.
DeploymentL74-L80How to install, configure, and run Azure AI Content Safety Docker containers for text, image, and prompt shield analysis in your own environment.
分类行范围描述
故障排查L36-L40诊断并解决Azure AI Content Safety API错误，包括HTTP状态码、常见故障原因及推荐的修复或重试方案。
最佳实践L41-L45调整Content Safety的阈值、类别和提示以减少误分类，以及平衡安全性、召回率和用户体验的策略。
决策制定L46-L51指导将应用从Content Safety预览版迁移至正式版（GA），以及决定何时及如何使用受限访问的Content Safety功能和模型。
架构与设计模式L52-L56结合云、混合和本地设备Azure AI Content Safety的架构指导，包括设计模式、部署选项和集成策略。
限制与配额L57-L63语言覆盖范围、自定义安全类别的构建与训练，以及检测模型输出中的受保护/第三方代码。
安全L64-L68Azure AI Content Safety如何加密静态数据的详细信息，包括加密模型、密钥管理选项和合规性/安全注意事项。
配置L69-L73在Azure AI Content Safety中配置和使用文本阻止列表，包括创建、管理和应用自定义阻止术语以过滤有害或不需要的内容。
部署L74-L80如何在自有环境中安装、配置和运行用于文本、图像和prompt shield分析的Azure AI Content Safety Docker容器。

Troubleshooting

故障排查

TopicURL
Resolve Azure AI Content Safety API error codeshttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/response-codes
主题链接
解决Azure AI Content Safety API错误代码https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/response-codes

Best Practices

最佳实践

TopicURL
Reduce false positives and negatives in Content Safetyhttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/improve-performance
主题链接
减少Content Safety中的误报和漏报https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/improve-performance

Decision Making

决策制定

TopicURL
Migrate apps from Content Safety preview to GAhttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/migrate-to-general-availability
Decide when to use limited access Content Safety featureshttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/limited-access
主题链接
将应用从Content Safety预览版迁移至正式版https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/migrate-to-general-availability
决定何时使用受限访问的Content Safety功能https://learn.microsoft.com/en-us/azure/ai-services/content-safety/limited-access

Architecture & Design Patterns

架构与设计模式

TopicURL
Design hybrid and on-device Content Safety solutionshttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/embedded-content-safety
主题链接
设计混合和本地设备Content Safety解决方案https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/embedded-content-safety

Limits & Quotas

限制与配额

TopicURL
Check language support for Azure AI Content Safetyhttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/language-support
Create and train custom categories with Content Safetyhttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-custom-categories
Use protected material detection for code outputshttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-protected-material-code
主题链接
查看Azure AI Content Safety的语言支持https://learn.microsoft.com/en-us/azure/ai-services/content-safety/language-support
使用Content Safety创建和训练自定义类别https://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-custom-categories
对代码输出使用受保护材料检测https://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-protected-material-code

Security

安全

TopicURL
Understand data-at-rest encryption in Content Safetyhttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/encrypt-data-at-rest
主题链接
了解Content Safety中的静态数据加密https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/encrypt-data-at-rest

Configuration

配置

TopicURL
Configure and use text blocklists in Content Safetyhttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/use-blocklist
主题链接
在Content Safety中配置和使用文本阻止列表https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/use-blocklist

Deployment

部署

TopicURL
Deploy image analysis Content Safety container with Dockerhttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/image-container
Install and run Azure Content Safety Docker containershttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/install-run-container
Run Prompt Shields Content Safety container for prompt attackshttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/prompt-shields-container
Deploy text analysis Content Safety container with Dockerhttps://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/text-container
主题链接
使用Docker部署Content Safety图像分析容器https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/image-container
安装并运行Azure Content Safety Docker容器https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/install-run-container
运行Prompt Shields Content Safety容器以防范提示攻击https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/prompt-shields-container
使用Docker部署Content Safety文本分析容器https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/containers/text-container