monday

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official @membranehq/cli tool from the npm registry. This package is the primary interface for the Membrane platform and is expected for this skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it retrieves data from Monday.com boards and items. \n
  • Ingestion points: Data enters the agent context via actions like list-items, list-updates, and get-board. \n
  • Boundary markers: The instructions do not specify the use of delimiters or markers for the data retrieved from external sources. \n
  • Capability inventory: The skill possesses the capability to perform write and delete operations (e.g., create-item, update-item-column-values, delete-board) and execute arbitrary API requests through the membrane request proxy. \n
  • Sanitization: No explicit sanitization or filtering of external data is defined in the workflow instructions.
  • [COMMAND_EXECUTION]: The skill utilizes the membrane CLI to execute project management tasks. The commands are structured and restricted to the capabilities provided by the authenticated connector.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 02:39 PM