スキル azure-ai-contentsafety-java
📦

azure-ai-contentsafety-java

安全 🔑 環境変数🌐 ネットワークアクセス

Build content moderation apps with Azure AI

Moderate harmful content automatically in your applications. Azure AI Content Safety SDK for Java detects hate speech, violence, sexual content, and self-harm with configurable severity thresholds.

対応: Claude Codex Code(CC)
🥉 74 ブロンズ
1

スキルZIPをダウンロード

2

Claudeでアップロード

設定 → 機能 → スキル → スキルをアップロードへ移動

3

オンにして利用開始

テストする

「azure-ai-contentsafety-java」を使用しています。 Analyze user comment for hate speech and violence

期待される結果:

Hate: Severity 2 (low confidence), Violence: Severity 0 (not detected). Content passes moderation threshold.

「azure-ai-contentsafety-java」を使用しています。 Check image for adult content

期待される結果:

Sexual category detected at Severity 6. Recommendation: Block content per policy threshold of 4.

「azure-ai-contentsafety-java」を使用しています。 Validate message against custom blocklist

期待される結果:

Blocklist hit detected: Item ID abc123 matched term variant. Content blocked per haltOnBlocklistHit setting.

セキュリティ監査

安全
v1 • 2/24/2026

Static analyzer produced false positives due to misinterpreting Markdown documentation. All 33 external_commands findings are Java code examples in Markdown fences, not shell execution. Network findings are example URLs for configuration. Environment variable access is standard Azure SDK pattern. No actual security issues detected.

1
スキャンされたファイル
288
解析された行数
2
検出結果
1
総監査数

リスク要因

🔑 環境変数 (1)
SKILL.md:34-35
🌐 ネットワークアクセス (2)
SKILL.md:148 SKILL.md:264-265
監査者: claude

品質スコア

38
アーキテクチャ
100
保守性
87
コンテンツ
50
コミュニティ
100
セキュリティ
91
仕様準拠

作れるもの

Social Platform Moderation

Automatically screen user-generated posts and comments for harmful content before publication. Configure severity thresholds to match community guidelines.

Customer Support Filtering

Detect abusive messages in support tickets and chat systems. Route flagged content to human reviewers while allowing legitimate messages through.

Marketplace Content Review

Scan product listings, reviews, and images for policy violations. Maintain custom blocklists for brand-specific prohibited terms.

これらのプロンプトを試す

Basic Text Analysis 
Analyze this text for harmful content using Azure AI Content Safety: [paste text]. Return severity scores for each category.
Configured Category Analysis 
Analyze [text] for hate and violence categories only. Use 8 severity levels output. Stop if blocklist hit occurs.
Image Moderation from URL 
Check the image at [URL] for harmful content. Report categories with severity >= 4. Format results as a moderation decision.
Blocklist Management Workflow 
Create a blocklist named [name] with description [desc]. Add these terms: [terms]. Then analyze [text] against this blocklist with halt on hit enabled.

ベストプラクティス

  • Read Azure SDK documentation for authentication and client configuration before implementation
  • Set severity thresholds based on your risk tolerance - severity 4+ is typical for strict moderation
  • Allow 5 minutes for blocklist changes to propagate before testing new entries
  • Cache analysis results for repeated content to reduce API calls and latency

回避

  • Hardcoding credentials instead of using environment variables or DefaultAzureCredential
  • Requesting all harm categories when only specific ones are needed - increases latency and cost
  • Blocking severity 0 content - this creates false positives for borderline cases
  • Synchronous API calls in high-throughput scenarios - use async patterns for batch processing

よくある質問

What Azure subscription do I need for Content Safety?
You need an Azure subscription with a Content Safety resource provisioned. Free tier includes 5,000 transactions per month for testing.
How do I authenticate the SDK?
Use either API key authentication with KeyCredential or Azure AD authentication with DefaultAzureCredential for production environments.
Can I customize harm detection thresholds?
Yes, set outputType to 8 severity levels and apply your own threshold filtering. The SDK returns numeric severity scores you can evaluate.
How quickly do blocklist updates take effect?
Blocklist changes typically propagate within 5 minutes. Plan accordingly when adding newly discovered problematic terms.
Does the SDK support async operations?
Yes, the Azure SDK supports asynchronous patterns. Use async client methods for non-blocking operations in high-throughput applications.
What image formats are supported?
The API accepts common image formats including PNG, JPEG, and BMP. Images can be provided as binary data or accessible blob URLs.

開発者の詳細

作成者

sickn33

ライセンス

MIT

リポジトリ

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/azure-ai-contentsafety-java

参照

main

ファイル構成

📄 SKILL.md