trello-automation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly directs the agent to call Trello API endpoints (e.g., TRELLO_GET_MEMBERS_BOARDS_BY_ID_MEMBER, TRELLO_GET_SEARCH, TRELLO_GET_BOARDS_BY_ID_BOARD) to fetch user-generated board/card data, descriptions, comments, and attachments, which the agent must read/interpret as part of workflows (searching, selecting, moving, or updating cards) and thus could allow indirect prompt-like instructions to influence actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill requires adding and calling the Rube MCP endpoint (https://rube.app/mcp) at runtime and explicitly instructs to call RUBE_SEARCH_TOOLS to fetch current tool schemas, so remote content from that URL can alter available tools and thus directly influence agent instructions.