soveren

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent or user to install the @membranehq/cli package globally via npm. This is an official tool provided by the vendor for managing integrations.
  • [COMMAND_EXECUTION]: The instructions guide the agent to perform various system operations using the membrane CLI, such as logging in, searching for connectors, and running actions.
  • [PROMPT_INJECTION]: The skill facilitates the processing of data from the external Soveren platform, which introduces a potential surface for indirect prompt injection.
  • Ingestion points: Data retrieved from the Soveren API via the membrane action run and membrane request commands (SKILL.md).
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: The skill allows the agent to execute actions (membrane action run) and perform network requests to the Soveren API (membrane request).
  • Sanitization: Not present; the skill assumes the agent will handle tool outputs safely.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 10:49 PM