enable-banking

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the official @membranehq/cli package from the npm registry, which is a legitimate vendor resource for managing the integration.
  • [COMMAND_EXECUTION]: The membrane CLI is used to perform account authentication, search for actions, and execute banking transactions. These commands are part of the core functionality provided by the vendor.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from action outputs and search results (e.g., from membrane action run and membrane action list) which are interpolated into the agent context. There are no explicit boundary markers or sanitization steps identified in the instructions for these ingestion points, although the skill's capabilities are limited to the actions available through the Membrane connection.
  • [DATA_EXFILTRATION]: No unauthorized network exfiltration or sensitive file access was detected. Authentication and data management are centralized within the Membrane platform.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 03:49 AM
Security Audit — agent-trust-hub — enable-banking