web-intelligence-router

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly describes this as a "Web 検索・読取・抽出・操作・巡回" router that automatically selects web acquisition methods, and scripts/router.py calls WebIntelligenceRouter.execute and returns extracted_data/evidence/citations—showing it fetches and interprets open web content that can influence agent actions.