elasticsearch-cluster-health
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for read-only diagnostics of Elasticsearch clusters. It explicitly instructs the agent never to mutate cluster state and to only provide remediation advice to the operator.
- [EXTERNAL_DOWNLOADS]: The skill references the official
elasticCLI repository (github.com/elastic/cli) for environment configuration. This is a trusted vendor resource. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Elasticsearch cluster APIs (health, allocation, cat shards). While it lacks boundary markers and explicit sanitization for this data, the skill is constrained to read-only diagnostic capabilities across all scripts, significantly limiting the risk of exploitation via indirect injection.
Audit Metadata