blend

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the '@membranehq/cli' package via npm. This is an official tool provided by the vendor 'membranedev' (as indicated by the author metadata and repository context) for interacting with their platform.
  • [COMMAND_EXECUTION]: The skill uses 'membrane' CLI commands for authentication, connection management, and action execution. These operations are within the scope of the skill's functionality and use the vendor's specialized tooling.
  • [CREDENTIALS_UNSAFE]: The skill leverages the Membrane CLI's secure authentication flow (OAuth-based/browser login), which manages secrets server-side and prevents the need for hardcoded API keys or manual credential entry.
  • [DATA_EXFILTRATION]: Data transfer occurs through the Membrane CLI and is directed to the Membrane platform and Blend API for processing. No suspicious or unauthorized exfiltration patterns were observed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 08:46 PM
Security Audit — agent-trust-hub — blend