kibana-alerting-rules
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the
elasticCLI to perform management operations against Kibana. The use of this command-line tool is standard practice for administrative interactions with Elastic Stack components and follows the intended primary purpose of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data in the form of Kibana alerting rules, which represents a theoretical injection surface if rules are maliciously crafted.
- Ingestion points: Rule metadata is fetched via the Kibana
_findand specific ruleGETendpoints inSKILL.md. - Boundary markers: None are specified; the agent is instructed to report rule names and IDs directly to the user.
- Capability inventory: The skill possesses write and lifecycle management capabilities (create, update, delete, mute, snooze) via the
elastic kb alertingCLI commands. - Sanitization: No explicit content sanitization or validation of the ingested rule data is defined before it is processed or displayed.
- [EXTERNAL_DOWNLOADS]: The documentation provides links to the official Elastic CLI GitHub repository and Terraform provider documentation. These are trusted vendor resources and are documented neutrally for installation and reference purposes.
Audit Metadata