trello-automation

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflows explicitly call Trello API endpoints (e.g., TRELLO_GET_SEARCH, TRELLO_GET_BOARDS_BY_ID_BOARD, TRELLO_GET_MEMBERS_BOARDS_BY_ID_MEMBER) to fetch user-generated board/card/comment/attachment content from Trello, which the agent must parse and use to decide and perform actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires connecting to Rube MCP at https://rube.app/mcp and explicitly instructs calling RUBE_SEARCH_TOOLS at runtime to fetch current tool schemas that directly control the agent's available tools/instructions, making this an external runtime dependency that can influence agent behavior.