monday-automation

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Monday.com boards, including item names, column values, and update threads, which act as untrusted input. There are no explicit boundary markers or instructions to ignore embedded commands within this data. The skill possesses extensive capabilities, including creating boards, items, and executing raw GraphQL mutations, creating a surface where malicious board content could potentially influence agent behavior.
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of a remote MCP server at https://rube.app/mcp. This connects the environment to a third-party infrastructure that is not part of the standard trusted vendor list.
  • [COMMAND_EXECUTION]: The tool MONDAY_CREATE_OBJECT provides a raw GraphQL interface for the agent. This allows for the execution of complex mutations and queries that bypass the abstractions of standard tools, which could be exploited if the agent is misled by data-driven inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 03:12 AM
Security Audit — agent-trust-hub — monday-automation