backlinks-domain-intersection

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow calls a runtime HTTP endpoint (curl to https://ai-factory.frevana.com/service/backlinks/domain-intersection) and then reads the returned response body as text (scripts/get_backlinks_domain_intersection.sh:335-345) and prints it (:350), which can be treated as outsider-authored free text that the agent may ingest into the LLM context.