ai-search-optimization

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

• Third-party content exposure detected (high risk: 0.75). The required workflow is a “manual prompt-audit” that asks the user’s target queries across external AI engines and then “reads the cited sources,” which implies the agent ingests outsider-authored free text from those engines’ responses and/or the cited pages at runtime (public web/engine output), creating an indirect prompt-injection risk.