mediamath

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the @membranehq/cli package globally via npm. This is the official command-line interface provided by the vendor (Membrane) to interact with their services.
  • [COMMAND_EXECUTION]: Instructions include the use of several membrane CLI commands for logging in, connecting to MediaMath, and executing actions. These commands are the primary intended interface for the skill's functionality.
  • [CREDENTIALS_UNSAFE]: The skill explicitly instructs the agent to let the platform handle credentials server-side and warns against asking the user for API keys or tokens, which aligns with secure credential management practices.
  • [DATA_EXPOSURE]: Data retrieved from MediaMath (e.g., reports, campaign data) is processed through the CLI. The skill encourages using pre-built actions which provide structured data and built-in handling for common API patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 12:06 PM