value-proposition-canvas

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow ingests verbatim customer quotes and interview/synthesis text from discovery/customer-interview-script/ and discovery/interview-synthesis/, which are outsider-authored free-form messages (customer-provided language) that can contain indirect prompt-injection payloads.