blog-factcheck

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

• Third-party content exposure detected (high risk: 0.85). The required workflow ingests the target blog post text (Step 1) and, for cited claims, fetches arbitrary outsider-authored web pages at runtime via WebFetch (Step 3), then searches their returned content for numeric values—this is direct free-text from public web sources into the LLM context.