interpreting-culture-index

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

• Third-party content exposure detected (high risk: 0.75). The required workflow can ingest outsider-authored free text when the user selects “Interview transcript only” / “Predict traits from interview” (workflows/predict-from-interview.md and downstream debrief), because the transcript quotes are user-provided text from an interviewer/candidate that the operating user did not author.