makini

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli tool, which is an official package provided by the vendor (membranedev).
  • [COMMAND_EXECUTION]: The skill uses shell commands to interact with the Membrane CLI for authentication and running actions.
  • [PROMPT_INJECTION]: The skill processes data from an external SaaS platform (Makini), presenting an indirect prompt injection surface.
  • Ingestion points: Data is received through the output of the membrane action run command.
  • Boundary markers: Not present; data is not delimited with instructions to ignore embedded commands.
  • Capability inventory: Includes the ability to execute CLI commands and interact with external APIs through the Membrane connector.
  • Sanitization: No validation or sanitization of the external data is specified before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 10:10 PM