kibana
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses shell commands to interact with the
@useclawlink/clitool for managing and querying Kibana resources. - [EXTERNAL_DOWNLOADS]: Fetches the
@useclawlink/clipackage from the official NPM registry usingnpxat runtime. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the execution of Kibana actions based on user descriptions and input parameters.
- Ingestion points: Ingests user intent for actions and specific JSON input data via the
npx @useclawlink/clicommand interface defined inSKILL.md. - Boundary markers: Includes clear instructions for the agent to perform read actions first and obtain user confirmation before any write operations.
- Capability inventory: The skill has the capability to execute shell commands (
npx) which can modify remote Kibana state (e.g., deleting alerts, connectors, or saved objects). - Sanitization: Utilizes a human-in-the-loop confirmation model for state-changing operations.
Audit Metadata