cnki-journal-search

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly navigates to and scrapes the public CNKI site (https://navi.cnki.net/knavi) via evaluate_script, extracts and interprets page text/links, and can auto-navigate to detail pages—so untrusted third‑party page content can directly influence agent actions.