Skills
skills/membranedev/application-skills/quickmailio/Gen Agent Trust Hub

quickmailio

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package globally using npm to provide the necessary tooling for the integration.
  • [COMMAND_EXECUTION]: The agent uses shell commands to authenticate with Membrane, create connections, and run actions against the QuickMail.io API.
  • [PROMPT_INJECTION]: The skill processes data from QuickMail.io, such as prospect information and email bodies, which are provided by external users. * Ingestion points: Data is entered into the agent context via membrane action run outputs. * Boundary markers: No delimiters or ignore-instructions are specified for the external data. * Capability inventory: The agent can manage connections and execute arbitrary actions via the CLI. * Sanitization: The skill does not include steps to sanitize or validate the external data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 08:42 PM