azure-ai-contentsafety-ts
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of official Microsoft Azure SDK packages, including @azure-rest/ai-content-safety, @azure/identity, and @azure/core-auth, from the public npm registry.
- [COMMAND_EXECUTION]: Documentation provides standard npm install commands to set up the environment for interacting with Azure services.
- [PROMPT_INJECTION]: The skill processes untrusted user-provided content for moderation, which establishes an indirect prompt injection surface.
- Ingestion points: External content enters through the text and image fields in analysis requests within SKILL.md.
- Boundary markers: The examples do not include explicit delimiters or instructions to ignore commands within the content being moderated.
- Capability inventory: The skill is capable of performing network requests to Azure AI endpoints and reading local files for image processing.
- Sanitization: No pre-sanitization is demonstrated as the skill itself serves as the moderation layer.
Audit Metadata