story-to-web

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

• Third-party content exposure detected (medium risk: 0.65). Outsider free text can enter the LLM context via Step 0/2 reading the runtime source_path narrative files (user-supplied files are not vetted, so their contents may be outsider-authored) and then extracting/using their prose throughout Steps 2–6 to generate the web-brief.