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_textparameter inSearchClient.searchand document content fields (e.g.,content,title) inSearchClient.upload_documentsingest 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