reg-gap-analysis

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

• Third-party content exposure detected (high risk: 0.90). Flagged because the SKILL.md workflow explicitly requires using legal retrieval connectors and web/online searches to "检索当前有效的要求" and performs a "检索连接器预检" (with instructions to include [联网检索 — 需复核] web/search citations), meaning the agent will fetch and interpret untrusted public webpages/regulatory sources that can materially affect its gap-analysis decisions.