super-search

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

• Third-party content exposure detected (high risk: 0.95). Outsider free text can enter the LLM context via Step 4→5: fetch.mjs retrieves arbitrary web page content for runtime-supplied URLs (from Step 3 search results) and passes the fetched content/markdown through SUPER_SEARCH_FETCHED into scripts/analyze.ts, which then extracts excerpts and forwards them into the report generation context.