trello

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to connect to Trello via the Membrane CLI and run actions against Trello boards/cards (user-generated content like card descriptions and comments), meaning the agent will fetch and interpret untrusted third-party content from Trello that could influence subsequent actions.