backlinks-bulk-ranks

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

• Third-party content exposure detected (high risk: 0.70). The required workflow calls Frevana’s /service/backlinks/bulk-ranks via curl, then reads the HTTP response body as text (raw = response_path.read_text(...)) and prints it to stdout, so any free-text content in the provider’s response (outsider-authored) is ingested into the agent/LLM context.