elasticsearch-migration

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data including Elasticsearch mappings, Query DSL, and documentation fetched via WebFetch, creating a potential surface for indirect instructions to influence agent behavior.
  • Ingestion points: External data is ingested from user-provided Elasticsearch configurations and documentation fetched from docs.vespa.ai and github.com/elastic (referenced in SKILL.md and docs/fetching-docs.md).
  • Capability inventory: The skill uses tools for file system manipulation (creating application packages), network operations (fetching documentation and feeding data), and shell command execution (Vespa and Elasticsearch CLI tools).
  • Boundary markers: The instructions do not specify the use of strict delimiters or protective wrappers when interpolating untrusted data into the agent's context.
  • Sanitization: There is no mention of explicit validation or sanitization of the content retrieved from external sources before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves documentation and migration utilities from official sources, including docs.vespa.ai, github.com/vespa-engine, and github.com/elastic.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 12:58 PM