evergreen-content-refresher

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

• Third-party content exposure detected (high risk: 0.85). At runtime the workflow ingests outsider-authored free text from public web sources via exa-search (SERP results/snippets) and perplexity (web-retrieved “latest statistics” with sources), which is then pasted into the LLM prompt in Step 5 (“Competing content now outranking it: [paste excerpts]” and “Fresh data: [paste research]”).