xhs-ops-methods

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to browse and learn from Xiaohongshu "搜索结果页" / "发现页" and its posts and includes prompt templates that take "{爆款链接或原文}" as input (see SKILL.md and references/prompt-templates.md), meaning the agent will ingest user-generated, public social-media content that can influence its decisions and actions.