cubejs

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the official Membrane CLI (@membranehq/cli) via the npm registry. This is a legitimate tool provided by the vendor for managing connections.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Cube.js APIs, which is an inherent attack surface for indirect prompt injection.
  • Ingestion points: API responses from Cube.js via membrane action run or membrane request commands (SKILL.md).
  • Boundary markers: No specific instructions for using delimiters or ignore-markers are provided for the agent when processing external data.
  • Capability inventory: Uses the membrane CLI to perform network operations and data retrieval.
  • Sanitization: The instructions do not specify any explicit sanitization or validation steps for data returned from the Cube.js API.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 02:19 PM