algolia-crawler

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses the Algolia Crawler to fetch and extract content from user-supplied URLs/pages (public web content), which becomes readable text in the crawler’s extracted records and is then written into the index (and thus can later be retrieved into LLM context), creating an indirect prompt-injection path from outsider-authored page text.