trafilatura

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

• Third-party content exposure detected (high risk: 0.85). High: the required “Extract” workflow runs scripts/extract_url.py which invokes trafilatura -u <user-supplied URL> and ingests the fetched page’s extracted main text (stdout → envelope["text"]) into the agent’s LLM context; this is outsider-authored free text from public web content.