monday-automation

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires a connection to the external MCP server endpoint https://rube.app/mcp to access the Monday.com toolkit.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and acts upon untrusted data from external Monday.com boards.
  • Ingestion points: Untrusted data enters the agent context through tools like MONDAY_LIST_BOARD_ITEMS, MONDAY_ITEMS_PAGE, and MONDAY_LIST_SUBITEMS_BY_PARENT which retrieve item names and column values.
  • Boundary markers: The skill instructions do not specify any delimiters or safety markers to distinguish fetched board content from the agent's core instructions.
  • Capability inventory: The skill has the capability to modify state via MONDAY_CREATE_ITEM, MONDAY_UPDATE_ITEM, and raw GraphQL mutations using MONDAY_CREATE_OBJECT.
  • Sanitization: No sanitization, escaping, or validation of the content retrieved from Monday.com is implemented in the skill description.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:37 AM