figure-it-out

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow explicitly instructs the agent to “Open a todolist whose first item is to read the Principles section of the poteto-mode skill,” which means the agent will ingest outsider-authored free text from another skill’s documentation at runtime via that “read” step.