azure-ai-contentsafety-py
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary purpose is content moderation using the Microsoft Azure AI Content Safety service. It follows industry-standard patterns for authentication and API usage.
- [EXTERNAL_DOWNLOADS]: The skill references the 'azure-ai-contentsafety' Python package, which is the official SDK maintained by Microsoft. It also utilizes standard Azure identity and core libraries.
- [DATA_EXFILTRATION]: While the skill transmits data to external endpoints, these are official Microsoft Azure Cognitive Services endpoints (cognitiveservices.azure.com). This is expected behavior for a cloud-based AI service and does not constitute unauthorized exfiltration.
- [CREDENTIALS_UNSAFE]: The skill correctly demonstrates using environment variables for sensitive API keys rather than hardcoding them within the scripts.
Audit Metadata