streak

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

• Third-party content exposure detected (high risk: 0.80). The skill calls the Streak API to retrieve user-generated content such as email threads, box comments, files, and other record data (e.g., "Get Threads in a Box" and "Get Comments in a Box"), which can contain arbitrary untrusted third‑party text that the agent will read and act on.