tw-edu-lesson-plan-108

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly calls for WebSearch in Step 2 ("網路資料搜尋（WebSearch）") and the MCP section ("WebSearch（已啟用）") to fetch open-web materials that the agent is expected to read and use when constructing lesson plans, which exposes it to untrusted third‑party content that could carry indirect prompt injections.