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

pledgeling

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official NPM registry. This is a legitimate tool provided by the skill's vendor (Membrane) to facilitate platform integrations.
  • [COMMAND_EXECUTION]: The skill uses various shell commands through the membrane CLI (e.g., membrane login, membrane connect, membrane action run) to manage the Pledgeling lifecycle. These commands are restricted to the functionality of the Membrane platform.
  • [SAFE]: Authentication is handled server-side by Membrane, ensuring that sensitive API keys or OAuth tokens are never exposed within the skill's code or handled directly by the AI agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 05:37 PM
Security Audit — agent-trust-hub — pledgeling