azure-ai-contentsafety-ts

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [Official SDK Integration]: The skill utilizes official Microsoft Azure packages (@azure-rest/ai-content-safety, @azure/identity) to perform content moderation. These are recognized vendor resources for interacting with Azure services.
  • [Credential Management]: Security-conscious patterns are used for handling sensitive information, such as recommending the use of environment variables for endpoints and API keys rather than hardcoding them.
  • [Network Operations]: The skill connects to official Azure service endpoints (cognitiveservices.azure.com and core.windows.net) to perform text and image analysis. These operations are essential for the skill's primary functionality.
  • [File System Access]: Examples include reading a local image file ('./image.png') to convert it to base64 for analysis. This is a standard procedure for processing local media for remote moderation services.
  • [Data Ingestion Surface]: As a moderation tool, the skill is designed to process untrusted user-generated content (text and images). It includes structured error handling and type guards, which help manage the data safely.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 02:46 PM