cnki-journal-search

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses a runtime browser tool to open CNKI pages and then reads document.body.innerText (and link innerText) from the fetched site, which is outsider-authored free text that is ingested into the agent’s LLM context via the returned results/rendered output.