formtitan

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the global installation of the @membranehq/cli package from npm. This is the official command-line interface for the Membrane platform, which is required for the skill to function.
  • [COMMAND_EXECUTION]: The instructions involve executing various shell commands via the membrane CLI, including login, connect, and action run. These commands are used to manage authentication and interact with the FormTitan API as intended by the skill's primary purpose.
  • [REMOTE_CODE_EXECUTION]: The membrane action create and membrane action run commands allow for the dynamic generation and execution of integration logic. This behavior is a core feature of the Membrane platform's 'actions' system and is executed within the context of the user's Membrane account.
  • [PROMPT_INJECTION]: The skill includes instructions to search for and create actions using natural language intents (e.g., membrane action list --intent "QUERY"). While this represents a data ingestion point, it is handled by the Membrane CLI as part of its standard discovery and automation features.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 07:15 PM
Security Audit — agent-trust-hub — formtitan