typesense

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the official NPM registry. This utility is the vendor's primary tool for managing integrations.
  • [COMMAND_EXECUTION]: Several commands are provided for the membrane CLI to perform authentication (membrane login), connection management (membrane connect), and action execution (membrane action run). These are standard operations for the platform's intended use case.
  • [PROMPT_INJECTION]: The skill utilizes a pattern where natural language intents are passed to the CLI to discover or create actions, which represents an indirect prompt injection surface.
  • Ingestion points: The intent parameter in membrane action list and membrane action create (SKILL.md).
  • Boundary markers: None explicitly defined in the provided instruction templates.
  • Capability inventory: Execution of arbitrary connector actions via membrane action run (SKILL.md).
  • Sanitization: Validation and intent parsing are handled by the Membrane platform's backend infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 03:48 AM