azure-ai-translation-ts
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- Secure Secret Management: The skill correctly instructs users to manage sensitive credentials like API keys and subscription keys through environment variables (
process.env.TRANSLATOR_SUBSCRIPTION_KEY) and placeholders (<your-api-key>), rather than hardcoding them into scripts. - Official Package Usage: The skill references standard Azure SDK packages (@azure-rest/ai-translation-text, @azure-rest/ai-translation-document, and @azure/identity) for authentication and service interaction, which is the recommended approach for integrating with Azure services.
- Indirect Prompt Injection Surface: As this skill is designed to process external text for translation and language detection, it possesses an inherent attack surface for indirect prompt injection. Applications built with this skill should implement appropriate validation and sanitization for user-provided text input before it is sent to the translation API.
- Ingestion points: Text inputs provided to the
/translate,/transliterate, and/detectendpoints inSKILL.md. - Boundary markers: None explicitly used in the code samples.
- Capability inventory: Performs network requests to Azure AI services and writes files to the local file system using
node:fs/promises. - Sanitization: No explicit sanitization or filtering is shown in the provided examples.
Audit Metadata