liferay

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install and use @membranehq/cli, which is the official command-line interface provided by the vendor (Membrane) for interacting with their services.
  • [COMMAND_EXECUTION]: The instructions utilize the membrane CLI to perform operations such as logging into the platform, creating connections, and executing actions. These commands are essential for the skill's intended functionality and use the vendor's own tooling.
  • [PROMPT_INJECTION]: The skill uses natural language inputs for searching actions (--intent "QUERY") and defining new actions (membrane action create "DESCRIPTION"). While this constitutes an input surface for the platform's AI-driven features, it is the primary and intended method of interaction described in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 11:50 PM
Security Audit — agent-trust-hub — liferay