elk-kibana-dashboards
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to triage and analyze log data from Elasticsearch and Kibana, creating a surface for indirect prompt injection where malicious instructions embedded in logs could attempt to influence agent behavior.
- Ingestion points: Log data accessed via Kibana Discover, Elasticsearch DSL queries, and index patterns.
- Boundary markers: The instructions lack explicit directives for the agent to use delimiters or to disregard instructions found within the log data itself.
- Capability inventory: The skill guides the agent in generating queries and planning dashboards; it does not define standalone scripts with autonomous file system or network capabilities.
- Sanitization: There are no provided methods for sanitizing or filtering instructions from the external data being analyzed.
Audit Metadata