morning-brief

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

• Third-party content exposure detected (medium risk: 0.30). The skill runtime first collects user-provided context (date window, priority focus, and which sources are accessible) and then pulls data from connected sources including “email inbox,” which commonly contains outsider-authored free text (email bodies) that the LLM would ingest when generating the brief.