analyze-startup-feedback

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text when the user supplies customer feedback items (e.g., CSV/JSON/Markdown/text/transcripts/tickets/reviews or screenshots with extracted text) and then the agent “inspect[s] every supplied” item and “creates one immutable record per evidence item” from that content.