azure-search-documents-py

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by processing untrusted data from search queries and document indexing.
  • Ingestion points: The search_text parameter in SearchClient.search and document content fields (e.g., content, title) in SearchClient.upload_documents ingest external data into the agent's context.
  • Boundary markers: None identified in the provided code snippets to delimit untrusted user input from system instructions.
  • Capability inventory: The skill performs network operations to Azure Search endpoints and indexing operations (CRUD on documents and indexes).
  • Sanitization: There is no evidence of sanitization or validation of input strings before they are passed to the search or indexing functions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:10 PM