trello-automation
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to connect to an external MCP server at
https://rube.app/mcp. This endpoint belongs to the skill author and is the primary mechanism for facilitating the Trello integration. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing data from external Trello boards and cards which are not under the direct control of the agent.
- Ingestion points: Untrusted data enters the context through tools like
TRELLO_GET_SEARCH,TRELLO_GET_BOARDS_LISTS_BY_ID_BOARD, andTRELLO_GET_BOARDS_CARDS_BY_ID_BOARD. - Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to ignore instructions embedded within the retrieved Trello content.
- Capability inventory: The skill possesses significant write capabilities, including
TRELLO_ADD_CARDS(creation),TRELLO_UPDATE_CARDS_BY_ID_CARD(modification/movement), andTRELLO_ADD_CARDS_ID_MEMBERS_BY_ID_CARD(member assignment). - Sanitization: There is no evidence of sanitization or content validation performed on the retrieved Trello data before it is processed by the agent.
Audit Metadata