azure-search-documents-ts
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of official Microsoft Azure SDK packages (@azure/search-documents, @azure/identity) from the public npm registry for its core functionality.
- [PROMPT_INJECTION]: The skill implements search and indexing capabilities that ingest untrusted data from search queries and retrieved document contents. This creates a surface for indirect prompt injection where malicious content in an index could influence agent behavior if processed by an LLM without proper delimiters.
- Ingestion points: Document data processed during indexing via
uploadDocumentsand search results retrieved via thesearchmethod (SKILL.md). - Boundary markers: No explicit boundary markers or "ignore instructions" delimiters are defined in the provided implementation examples.
- Capability inventory: Network access to Azure AI Search API endpoints and index management capabilities (SKILL.md).
- Sanitization: The provided code snippets do not include explicit sanitization or filtering logic for data retrieved from search results before it is presented to the agent.
Audit Metadata