trello-automation

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the user to configure a remote MCP server at https://rube.app/mcp. This external service acts as a proxy for Trello API calls and manages authentication.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from Trello boards that could contain malicious instructions.
  • Ingestion points: Data enters the agent's context through tools like TRELLO_GET_SEARCH and TRELLO_GET_BOARDS_CARDS_BY_ID_BOARD which read card titles, descriptions, and comments.
  • Boundary markers: The skill lacks explicit instructions or delimiters to isolate data retrieved from Trello from the agent's internal logic.
  • Capability inventory: The skill possesses significant write capabilities, including TRELLO_ADD_CARDS, TRELLO_UPDATE_CARDS_BY_ID_CARD, and TRELLO_ADD_CARDS_ATTACHMENTS_BY_ID_CARD, which could be abused if an injection is successful.
  • Sanitization: No sanitization or validation logic is defined for the content retrieved from external Trello sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 09:33 AM