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

golioth

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the NPM registry. This is an official tool provided by the vendor to interface with their platform.
  • [COMMAND_EXECUTION]: The skill defines various CLI commands for the agent to execute, including authentication tasks (membrane login), service connection (membrane connect), and running predefined platform actions (membrane action run).
  • [SAFE]: The skill follows security best practices by delegating credential management to a centralized platform rather than requesting raw API keys or secrets from the user. All network interactions are performed through official vendor tooling.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:02 AM
Security Audit — agent-trust-hub — golioth