addsearch

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package globally via npm. This is a vendor-owned CLI tool required for the skill's operation within the Membrane ecosystem.
  • [CREDENTIALS_UNSAFE]: The skill explicitly promotes secure practices by instructing the agent to never ask for API keys or tokens. Instead, it uses a managed connection flow where credentials are handled server-side by the Membrane platform.
  • [COMMAND_EXECUTION]: The skill utilizes standard shell commands (membrane action run, membrane action list) to interact with the AddSearch API through the Membrane CLI. These commands are part of the intended integration workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 04:46 PM