event-sources

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

• Third-party content exposure detected (high risk: 0.95). The required runtime workflow uses bun run .../extract-content.js "<url>" to fetch and Readability-extract text from multiple outsider-authored public web pages (e.g., INDEX Berlin, KW Institute, Berlinische Galerie, visitBerlin), which then gets ingested into the agent’s LLM context via qurl add/search results.