backlinks-bulk-new-lost-referring-domains

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

• Third-party content exposure detected (high risk: 0.85). The required workflow calls a runtime HTTP endpoint and then reads the provider’s response body from RESPONSE_FILE into the script’s Python JSON-validation step and prints it to stdout (scripts/get_backlinks_bulk_new_lost_referring_domains.sh:326-344), so outsider-authored free text (the API response) is ingested into the LLM context.