yuandian-law-search

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

• Third-party content exposure detected (high risk: 0.90). The skill's CLI (scripts/yd_search.py) explicitly POSTs to the external YuanDian API (BASE_URL http://aiapi.ailaw.cn:8319) and ingests returned public law texts and case bodies (fields like "法条全文" and "正文" and provided "法规链接"/"案例链接") which are formatted and advertised in SKILL.md as outputs "可直接用于... AI 分析", so untrusted third‑party content is read and can materially influence subsequent analysis.