brex

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the NPM registry, which is the official tool provided by the vendor.
  • [COMMAND_EXECUTION]: The skill uses the membrane command-line utility to interact with the Brex API. This includes listing users, cards, and expenses, as well as creating or running integration actions.
  • [CREDENTIALS_UNSAFE]: The skill adheres to security best practices by explicitly advising the agent to never request API keys or tokens from the user, relying instead on the platform's secure connection management.
  • [SAFE]: All external references, including the CLI tool and the getmembrane.com domain, belong to the skill's author (membranedev) and represent intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 03:19 PM
Security Audit — agent-trust-hub — brex