Skills
skills/membranedev/application-skills/tink/Gen Agent Trust Hub

tink

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to install and run the official Membrane CLI (@membranehq/cli) to interact with Tink services. It utilizes commands like membrane login, membrane connect, and membrane action run to manage financial data and workflows.
  • [EXTERNAL_DOWNLOADS]: Downloads the latest version of the Membrane CLI package from the public npm registry during the installation phase.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for processing user-supplied natural language through CLI parameters.
  • Ingestion points: User input is passed via --intent in membrane action list and --input in membrane action run commands.
  • Boundary markers: Not explicitly defined in the provided markdown instructions.
  • Capability inventory: The skill can execute actions on the Tink platform and create new actions via membrane action create.
  • Sanitization: Not visible in the static instructions; behavior depends on the underlying CLI implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 09:41 AM