ljg-paper-flow

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly accepts arXiv links, paper URLs, and PDFs and calls ljg-paper to read/interpret those external papers as part of its required workflow (see SKILL.md "执行" step 1 and step 2 A), so untrusted third-party content can influence generated outputs and downstream actions.