azure-ai-translation-ts
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs official Azure SDK packages (
@azure-rest/ai-translation-text,@azure-rest/ai-translation-document, and@azure/identity) from the npm registry. These are well-known, trusted libraries from Microsoft. - [CREDENTIALS_UNSAFE]: The skill correctly instructs users to manage sensitive credentials (like API keys) using environment variables (
process.env.TRANSLATOR_SUBSCRIPTION_KEY). It uses placeholders like<your-api-key>in documentation, which is standard practice and does not expose actual secrets. - [DATA_EXFILTRATION]: Network operations are directed towards official Microsoft Azure endpoints (
api.cognitive.microsofttranslator.comandcognitiveservices.azure.com). These are legitimate destinations for the service described. - [INDIRECT_PROMPT_INJECTION]: While the skill processes external text for translation, it does so using standard API patterns. The documentation includes best practices like checking for unexpected responses and using time-limited Shared Access Signature (SAS) tokens for document access, which helps mitigate unauthorized data access risks.
Audit Metadata