azure-ai-contentsafety-py
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- External Package Installation: The skill includes instructions to install the
azure-ai-contentsafetypackage via pip. This is the official Python SDK for the Azure AI Content Safety service and is a standard requirement for utilizing the described capabilities. - Data Ingestion Surface: The skill is designed to process and analyze potentially untrusted user-generated data, such as text and images, for harmful content. This creates a surface for indirect prompt injection, where malicious instructions could be embedded in the data being analyzed. However, the skill itself is intended to be the security control that detects and mitigates such content.
- Credential Management Best Practices: The skill follows security best practices by explicitly recommending the use of
DefaultAzureCredentialand managed identities to avoid the risks associated with hardcoded API keys or connection strings.
Audit Metadata