tw-edu-formative-assessment

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly enables "WebSearch（已啟用）" in the MCP/Claude connector and states it will "搜尋最新課綱資料、教學素材、時事情境" (search public web resources) which the agent is expected to read and use when generating assessments, exposing it to untrusted third‑party content.