documint

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the official Membrane CLI (@membranehq/cli) from the public NPM registry. This is a standard installation of a vendor-provided tool required for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill utilizes several CLI commands (e.g., membrane login, membrane connect, membrane action run) to interact with the Documint API. These commands are part of the intended integration logic and operate within the scope of the Membrane platform.
  • [CREDENTIALS_UNSAFE]: The skill follows security best practices by explicitly instructing the agent not to ask for or handle raw API keys. Instead, it uses a managed connection system where authentication is handled server-side by the platform, preventing credential exposure in the local environment or agent logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 05:25 PM
Security Audit — agent-trust-hub — documint