gutenberg

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

• Third-party content exposure detected (high risk: 0.75). Yes—at runtime the required workflow downloads outsider-authored book text/HTML from Project Gutenberg (public web content) via urllib.request.urlopen, then reads it as UTF-8 prose (content.decode(...) / EPUB XHTML z.read(...).decode(...)) and writes/uses it as body/full_text, which can be fed into the agent’s LLM context by the surrounding system.