xiaohongshu-content-benchmark

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly scrapes public, user-generated Xiaohongshu content (see SKILL.md “Validated actor path” using easyapi/rednote-xiaohongshu-user-posts-scraper and scripts/build_xhs_benchmark_actor_input.mjs which accept profileUrls/keywords) and then normalizes and summarizes those posts (scripts/lib/xhs_common.mjs, analyze/rank scripts) to drive rankings, card-suggestions and follow-up actions, so untrusted third‑party content is read and can materially influence agent behavior.