plaud-recordings-to-google-calendar-events

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

• Third-party content exposure detected (high risk: 0.90). The required workflow fetches Plaud recordings’ full transcript (outsider-authored body text) and then uses an LLM prompt to “Extract Scheduling Commitments” from that transcript at runtime, so the transcript becomes LLM context (indirect prompt-injection risk).