yapily
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 package from the NPM registry. This is a vendor-owned resource belonging to membranedev.
- [COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands using the membrane CLI to manage connections and run actions.
- [PROMPT_INJECTION]: The skill processes external financial data from bank APIs, which constitutes an indirect prompt injection surface. Ingestion points: Data returned from membrane action run. Boundary markers: Not present in the skill instructions. Capability inventory: Use of the membrane CLI to execute actions and create new ones. Sanitization: No specific output validation or sanitization is described.
- [SAFE]: The skill leverages the Membrane platform to handle credentials server-side, which is a more secure alternative to storing API keys or tokens locally.
Audit Metadata