azure-ai-translation-ts
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external text and documents for translation, which acts as a potential ingestion point for instructions embedded in data.
- Ingestion points: The skill accepts text input for translation and document bodies in
SKILL.md. - Boundary markers: None are specified in the code examples to delimit translated content from agent instructions.
- Capability inventory: The skill performs network requests to Azure services and writes translated files to the local disk using
node:fs/promises. - Sanitization: There is no evidence of input validation or content sanitization within the provided implementation examples.
- [EXTERNAL_DOWNLOADS]: The installation instructions fetch official Azure libraries from the NPM registry, which belongs to a well-known and trusted technology organization.
- [SAFE]: The skill follows best practices for secret management by utilizing environment variables for API keys and recommends the use of time-limited Shared Access Signature (SAS) tokens for document storage access.
Audit Metadata