azure-ai-contentsafety-ts
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- Standard Secret Management: The skill correctly instructs users to manage sensitive information, such as
CONTENT_SAFETY_KEYandCONTENT_SAFETY_ENDPOINT, through environment variables rather than hardcoding them in the source code. - Secure Authentication Patterns: It supports
DefaultAzureCredentialfrom the@azure/identitypackage, which is a security best practice for Azure applications. This allows the skill to use Managed Identities or service principals in production, reducing the risk of long-lived credential exposure. - Trusted Dependency Usage: All referenced packages (
@azure-rest/ai-content-safety,@azure/identity, and@azure/core-auth) are official, well-known libraries from a trusted vendor (Microsoft), intended for their stated purpose of content moderation. - Neutral Infrastructure Use: The network operations described (targeting
cognitiveservices.azure.comandblob.core.windows.net) are standard endpoints for Azure AI and storage services, consistent with the skill's function.
Audit Metadata