kibana
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Utilizes the
membraneCLI to execute various shell commands for managing connections, searching for actions, and performing API requests. - [EXTERNAL_DOWNLOADS]: Instructs users to install the
@membranehq/clipackage globally from the NPM registry, which is the official tool provided by the vendor for this integration. - [PROMPT_INJECTION]: Identifies a surface for indirect prompt injection through the processing of data retrieved from Kibana endpoints.
- Ingestion points: External data is brought into the agent context via the output of
membrane action runandmembrane requestcommands. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the retrieved Kibana data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill maintains the ability to execute shell commands and perform network operations through the Membrane proxy.
- Sanitization: No evidence of validation or sanitization of the external data is present in the provided instructions.
Audit Metadata