azure-ai-contentsafety-java
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses official Microsoft Azure libraries for content moderation tasks, which are sourced from a trusted organization.- [CREDENTIALS_UNSAFE]: The skill correctly demonstrates using environment variables (
CONTENT_SAFETY_KEY) and theDefaultAzureCredentialclass for authenticating with Azure services, which is a recommended security practice to avoid hardcoding secrets.- [COMMAND_EXECUTION]: Local file system access is limited to reading image files (Files.readAllBytes) for the purpose of safety analysis, which is consistent with the skill's documented functionality.- [EXTERNAL_DOWNLOADS]: The skill references standard Maven dependencies and official Azure endpoints, which are well-known and trusted services.
Audit Metadata