shadow

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

• Third-party content exposure detected (high risk: 1.00). Flagged because SKILL.md's "Search Fallback Rule" explicitly requires calling external search / webpage scraping / APIs ("外部检索适配层：搜索引擎/网页抓取/API") to supplement information, meaning the agent will ingest untrusted public web content and use it to influence its decisions and next actions.