ljg-paper

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

• Third-party content exposure detected (high risk: 1.00). Yes — the SKILL.md "執行 → 獲取內容" steps explicitly fetch and ingest public third‑party sources (arxiv URL via WebFetch, PDF via Read, and WebSearch), so the agent will read and act on untrusted external content that could carry indirect prompt injections.