monday-automation
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from an external platform (Monday.com) and possesses the capability to modify that environment through automated tools.
- Ingestion points: Data enters the agent context via
MONDAY_LIST_BOARDS,MONDAY_LIST_BOARD_ITEMS, andMONDAY_LIST_SUBITEMS_BY_PARENT. - Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore potentially malicious instructions embedded in Monday.com item names or descriptions.
- Capability inventory: The skill provides write-access tools including
MONDAY_CREATE_BOARD,MONDAY_CREATE_ITEM,MONDAY_CHANGE_SIMPLE_COLUMN_VALUE,MONDAY_UPDATE_ITEM, and the powerfulMONDAY_CREATE_OBJECT(raw GraphQL mutation). - Sanitization: No sanitization or validation of external content is mentioned.
- [EXTERNAL_DOWNLOADS]: The skill directs the user to configure a remote MCP server at
https://rube.app/mcp. This domain is not identified as a well-known or trusted service provider, and the remote server mediates all interactions between the agent and the Monday.com API.
Audit Metadata