trello-automation

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [Unverifiable Dependencies & Remote Code Execution] (LOW): The skill references an external MCP server endpoint (https://rube.app/mcp). While this is a configuration for the MCP client and not a direct script execution, it establishes a dependency on an external service provider not listed in the trusted sources.
  • [Indirect Prompt Injection] (LOW): The skill is designed to read and search content from Trello boards which may contain untrusted data from other users.
  • Ingestion points: Card content and search results via TRELLO_GET_SEARCH and TRELLO_GET_BOARDS_CARDS_BY_ID_BOARD.
  • Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore instructions within Trello cards.
  • Capability inventory: The skill has broad Trello write permissions including TRELLO_ADD_CARDS, TRELLO_UPDATE_CARDS_BY_ID_CARD, and TRELLO_ADD_CARDS_ATTACHMENTS_BY_ID_CARD.
  • Sanitization: Absent; the agent is expected to process the raw strings returned by the Trello API.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 03:09 PM