asb-interview-report

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests user-provided “debriefs” (raw transcripts/notes) and harvests their verbatim text for drafting the report (“Phase A — Ingest” and “Phase B — The sweep (silent)”), so outsider-authored free text can be supplied via those files and then read by the LLM at runtime.