post-optimizer

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 1b "热点扫描与深入研究" explicitly requires using search tools to fetch and analyze open web sources (e.g., 官⽅网站/文档, GitHub, 用户评价, 社区讨论, 社交媒体 and other public webpages) and to integrate those user-generated and third‑party findings into the rewrite workflow, which clearly exposes the agent to untrusted external content that can influence decisions.