researching-gourmet-venues

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

• Third-party content exposure detected (high risk: 0.85). The required workflow’s runtime evidence collection step (“Evidence: For each candidate, write a full evidence block in notes.md with sources”) can ingest outsider-authored free text from public web content fetched at runtime (e.g., scraped/loaded ranking pages, Maps/aggregator pages, guide/editorial articles) into the LLM context.