api-search-elasticsearch
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for fetching data from external Elasticsearch clusters, which constitutes a potential surface for indirect prompt injection if the retrieved content is included in an agent's prompt without sanitization.
- Ingestion points: The skill demonstrates how to ingest external data via
client.searchinexamples/core.mdandclient.helpers.scrollSearchinexamples/pagination.md. - Boundary markers: The provided examples do not implement or recommend prompt boundary markers to separate untrusted search results from instructions.
- Capability inventory: The skill uses the
@elastic/elasticsearchlibrary for network operations andnode:fs(inexamples/bulk-operations.md) for file system access to read bulk data. - Sanitization: The code patterns do not include logic for sanitizing or validating the content returned from Elasticsearch queries.
Audit Metadata