azure-ai-contentsafety-java
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill provides patterns for analyzing external text and image content through classes like AnalyzeTextOptions and ContentSafetyImageData. As with any content moderation tool, there is a possibility that adversarial inputs could attempt to influence the analysis results. While the examples do not include explicit boundary markers or sanitization, they correctly demonstrate the usage of the SDK to obtain severity levels for further moderation logic.
- Secure Credential Management: The skill demonstrates secure practices by encouraging the use of environment variables and Azure Identity's DefaultAzureCredential for managing sensitive credentials like API keys or client secrets, which is consistent with Microsoft's recommended security patterns.
- Official Service Interaction: The skill facilitates communication with official Azure AI Content Safety services for text and image analysis. These network operations are intended for the primary purpose of the skill and target well-known vendor endpoints.
Audit Metadata